Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does add useful status/safety context: deprecated, decision-support-only, verify official source, and not for procurement/equivalence. It does not, however, describe what the operation actually does or what happens when invoked.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the most important signal, 'Deprecated'. It packs several constraints into one short block, though the repeated '=true' style is somewhat telegraphic.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though an output schema exists, the description leaves major gaps: the core purpose, query semantics, and selection criteria relative to sibling tools are absent. The warnings are useful, but an agent cannot confidently determine how to invoke or interpret this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only adds the restriction '不得輸入病人資料' (do not input patient data). It never explains what 'query' means or how 'limit' behaves, so it does not compensate for the missing parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the domain and status ('Deprecated TFDA operation') but never states that the tool compares products. It remains a vague purpose statement and relies on the tool name for the actual function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides strong when-not-to-use signals: deprecated, not validated for hospital deployment, not for procurement or equivalence, and no patient data. However, it does not state positive conditions for use or name an alternative sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral burden. It does disclose one important output trait ('no catalog is returned'), which helps set expectations. However, it does not mention read-only behavior, data freshness, authorization needs, or any potential side effects; the term 'reserved' is also left unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core purpose and appends a useful caveat. Every word earns its place, and there is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter status tool with an output schema, the description is largely sufficient: it identifies the resource and clarifies that no catalog is returned. The main gap is the lack of differentiation from sibling status tools and the unexplained term 'reserved,' but these do not prevent basic invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to clarify. The baseline of 4 applies because no parameter documentation burden exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Show') and resource ('reserved EQA/CAP status'), and adds a differentiator by noting 'no catalog is returned.' This makes the tool's basic purpose understandable, though it does not explicitly contrast it with sibling status tools like standards_status or get_data_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus the many sibling tools. There is no mention of context, exclusions, or alternatives. The caveat about catalog output is about behavior, not usage selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It includes several behavioral flags such as verify_current_official_source and does_not_confirm_current_acceptance, which disclose important limitations. However, these are presented as bare booleans without explanation of what they mean operationally, and the description does not describe the tool's behavior such as output format or side effects. The privacy restriction adds some context but is not enough to elevate the score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and starts with the main purpose, which is good. However, it appends a series of flags and a Chinese sentence without clear structure or integration, making it a bit cluttered. It is not overly verbose but could be more organized and concise by explaining the flags or folding them into the narrative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 2 parameters and no schema descriptions, the description is incomplete. It does not explain how to use the parameters, what the output will be, or when this tool is appropriate. The presence of an output schema helps but does not compensate for the lack of parameter and usage guidance. The caveats are present but not elaborated, leaving an agent with insufficient context to make a correct call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the parameters. The description does not mention 'query' or 'city' at all, providing no guidance on their format, semantics, or required values. This is a critical gap for an agent trying to construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Find CDC recognized-lab rows.' It is not a tautology and conveys the core function. However, it does not differentiate from siblings like search_lab_code or get_lab_scope, which also involve lab-related lookups, so it loses a point for lacking sibling distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It includes caveats like decision_support_only and not_validated_for_hospital_deployment, but these are limitations, not usage directions. The Chinese phrase '不得輸入病人資料' (do not enter patient data) is a restriction but not a usage guideline, and there is no mention of scenarios or comparison to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it delivers: it discloses that results are summaries only, that return content is raw official data not instructions to the AI, that patient data must not be input, and that results are not for procurement, equivalence, or promotional use. This is extensive behavioral disclosure beyond simple operation statements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is densely packed and front-loads the core behavior, but it is somewhat long and repeats similar restrictions (decision_support_only, not_for_procurement_or_equivalence, and later the advertising caveat). Each sentence contributes value given the lack of annotations, though some redundancy prevents a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and three parameters, the description is complete: it names the search dimension, pagination, summary-only results, the get_license alternative, and multiple usage restrictions. The existence of an output schema covers return-value details, so nothing critical is missing for correct tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must define parameters, and it does: 'name' is implied as manufacturer name, 'limit' is constrained to 1–5, and 'offset' is explained as pagination for viewing more results. This compensates fully for the missing schema-level parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description opens with a specific verb and resource: 'Find TFDA permit rows by manufacturer name only'. It clearly distinguishes the tool from alternatives by adding 'never by applicant' and later references get_license for full-field queries. The purpose is unmistakable even before looking at parameters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit when-not condition ('never by applicant'), an alternative tool for full details ('use get_license to query a single license number'), and concrete pagination guidance (limit 1–5, use offset for more). This is strong routing guidance with no ambiguity about how to use the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose several behavioral flags (decision_support_only, verify_current_official_source, not_validated_for_hospital_deployment, not_pre_submission_storage) and the patient-data restriction, which gives some context beyond what structured fields would provide. However, these flags are cryptic and unexplained, and the description does not mention what the tool returns or any side effects, so the disclosure is incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but it is not well-structured. It opens with a cryptic 'CDC compatibility alias' and then lists unformatted flags followed by a Chinese sentence. It does not front-load the primary purpose, and the information provided is dense but not organized for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description gives no indication of what the tool returns or how it fits into the overall workflow. With a single parameter and no explanation of its purpose or behavior, the description is severely incomplete for an agent to decide whether and how to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the 'disease' parameter. It does not state what values are valid, what format is expected, or how to provide it. The only relevant hint is 'do not input patient data,' which is a negative constraint but not a semantic explanation of the parameter's meaning or domain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'CDC compatibility alias' which is vague and does not state a specific action or resource. It does not explicitly say it retrieves collection methods for a disease, and the name 'get_collection_method' is only partially echoed. It reads more like a label than a purpose statement, leaving the agent to guess what the tool actually does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus any of the 21 sibling tools. The only usage hint is the Chinese sentence '不得輸入病人資料' (do not input patient data), which is a constraint on input content, not a selection criterion. No alternatives or exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description should carry the behavioral disclosure burden. It reveals deployment constraints and warns 'do not enter patient data' (不得输入病人资料), but it does not state whether the tool reads or mutates data, requires authorization, or has side effects. The caveats are useful for restrictions, not for understanding tool behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short and its flags are neatly listed, but no sentence earns a position in terms of helping invocation-the core purpose is still missing. It reads as a set of metadata flags rather than a real tool description, so the brevity is under-separation rather than concise adequacy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has one required, undocumented parameter and no annotations, the description is far from complete. Even with an output schema present, an agent lacks the minimal operational understanding needed to decide to call it. The description is too vague to compensate for the context-missing tool intent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The required param, subscript disease, is entirely undocumented; schema coverage is 0 percent, and the description does not mention it at all. The description does not explain what disease values are expected or how the parameter is used. The warning against patient data is only a loosely related input restriction, not a parameter semantic.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says only 'CDC compatibility alias', which conveys neither a specific action nor a resource, and never mentions what 'get_container' does. An agent cannot tell whether this tool retrieves, creates, or transforms container-related data. It is closer to a label than a purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives restrictions and caveats such as 'decision_support_only=true', 'not_validated_for_hospital_deployment=true', and 'not_pre_submission_storage=true', but it offers no guidance on when an agent should select this tool over the many sibling tools. It does not name any alternative or specify an actual use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates strictness and per-source granularity, but does not say whether the operation is read-only, whether any sources can be missing, or what kind of response shape to expect independent of the output schema. This is a minimal disclosure for a no-annotation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short, direct sentence with no filler. The core meaning is front-loaded, and the clarifying negation about a health score earns its place by shaping expectations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and the presence of an output schema, the description is mostly sufficient for a simple status-retrieval tool. It does not tell the agent when to choose this over related siblings, but the low complexity and output schema reduce the need for extensive behavioral detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to add about parameter meaning. The baseline for a parameterless tool is 4, and the description does not need to compensate for schema coverage gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Return strict per-source status'. It also clarifies the tool is not a single health score, which gives some differentiation from a generic status check. It does not name sibling distinctions, but the core purpose is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a mild negative usage signal by saying 'this is not a single health score', implying it should not be used for an overall health assessment. However, it gives no positive guidance about when to use this tool, no alternatives, and no distinction from sibling status-related tools such as standards_status or eqa_status.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It does mention several important traits: decision_support_only, not validated for hospital deployment, does not confirm current acceptance, and a warning against inputting patient data. However, it does not explain side effects, output behavior, or error conditions, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief and contains multiple distinct pieces of information, but it is not well-structured. The main purpose is vague and the flags are listed without context. The Chinese instruction is important but buried at the end; front-loading the query semantics would improve clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists, the description fails to explain when to use the tool, what the query parameter should contain, or how the returned data relates to CDC lab recognition. For a low-complexity tool, this is still insufficient because the core semantics are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter 'query' with zero description coverage. The tool description does not explain what 'query' means, its expected format, or examples. It only adds a constraint (no patient data), which is not an adequate substitute for semantic guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'CDC recognized-lab compatibility alias' hints at a compatibility check but never states the actual operation or what it returns. It lacks a specific verb like 'check' or 'retrieve' and does not clearly differentiate from sibling tools such as get_license or find_authorized_lab.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No context is provided about when to use this tool versus the many sibling search/query tools. There is no mention of scenarios, prerequisites, or exclusions. The description only lists internal flags, which do not guide tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it delivers: it explains exact matching, row-level behavior, validity versus recorded cancellation, and that output is raw official data rather than AI instructions. This goes well beyond a simple lookup description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in the first sentence, followed by structured caveats. It is longer than a trivial description, but nearly every sentence adds necessary constraints or interpretation guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter lookup with an output schema, the description covers exactness, source, field scope, validity nuance, and permissible uses. It does not explicitly address no-results behavior, but the output schema likely covers the return structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only shows a string named license_no with no description, so the tool description must compensate. It clarifies that the parameter is an exact TFDA permit number, adding meaning beyond the schema, though it does not give format examples or normalization details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: fetching all TFDA source rows for one exact permit number with all official fields. It explicitly notes each manufacturer row stays separate, which clearly distinguishes it from sibling tools like list_matching_license_records.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear usage constraints: decision support only, not for hospital deployment, not for procurement or equivalence, and no patient data. It does not name alternatives explicitly, but the exact-match wording and restrictions give strong context for when to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosing behavior. It explicitly states the tool is decision_support_only, requires verification of official source, is not validated for hospital deployment, and not for claim determination. It also warns against inputting patient data and clarifies the output is original official text, not AI instructions. This is meaningful beyond schema, though it does not explicitly state read-only nature or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief, front-loading the core purpose, then listing constraints and a Chinese usage note. It is efficient but slightly choppy with semicolon-separated flags; still, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a single required parameter and an existing output schema, the description provides key safety and usage constraints (decision support, no patient data, official text output). However, it does not describe the query format or what constitutes 'exact-code', which is essential for correct invocation. It is moderately complete but has notable gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It implies the query is an exact code ('exact-code notes') but does not specify format, allowed values, or examples. The description adds only minimal meaning beyond the parameter name 'query'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves NHI exact-code notes, providing a specific verb and resource. It does not explicitly contrast with sibling tools like get_submission_rule or search_payment_items, but the 'exact-code notes' phrasing distinguishes it from general search or submission rule retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives constraints (decision_support_only, not_for_claim_determination) but does not explain when to use this tool versus alternatives. No mention of conditions that select this tool over siblings such as get_submission_rule or search_payment_items.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses that output is raw official text rather than instructions for the AI, that the data must be verified against the current official source, and that it is not validated for hospital deployment or claim determination. These are meaningful behavioral warnings beyond a simple 'get' statement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the core purpose before the constraint flags and Chinese guardrails. It is slightly fragmented by the key-value flag list, but every part contributes useful information with no real filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives strong safety and usage context, and an output schema exists, so return values do not need explanation. However, the total absence of parameter guidance is a major gap: an agent cannot reliably invoke this tool without knowing what 'code' represents and how to provide 'as_of'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it does not explain either parameter. 'code' and 'as_of' are not mentioned, leaving the agent to guess what values are valid and what format 'as_of' should take.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Get current NHI points only,' which is a specific verb-resource pairing and the word 'only' narrows the scope. It is clear about what the tool returns, though it does not explicitly differentiate from sibling tools by name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage constraints: decision_support_only=true, not_for_claim_determination=true, not_validated_for_hospital_deployment=true, and the Chinese instruction '不得輸入病人資料' (do not input patient data). This gives clear when-not-to-use guidance, though it does not name alternative tools for other scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the disclosure burden, and it does disclose meaningful constraints: the data is decision-support-only, not pre-submission storage, not validated for hospital deployment, and current official sources must be verified. It also warns against entering patient data. What it omits is response/pagination behavior, but output schema exists and the tool is a simple read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and the main action is front-loaded. The flag list and the patient-data warning are terse and somewhat cryptic (e.g., '=true' syntax), but each clause carries information and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low schema coverage and one-parameter surface, the description could be complete, but it omits the accepted disease value format and doesn't route among the many sibling tools. The output schema plus safety flags cover return and usage constraints, so it is adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single 'disease' parameter is not explained in the schema or description. The description implies the tool is queried by disease and that patient data must not be passed, but it does not state accepted values, format, or codes. That leaves a real gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb-resource pair: 'Get CDC specimen rows,' which identifies the data source and broad action. It does not explicitly contrast with siblings like get_collection_method or get_transport_requirement, but the resource is specific enough to avoid obvious confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The boolean flags provide explicit context: decision_support_only, not_validated_for_hospital_deployment, and not_pre_submission_storage tell an agent when the result is and isn't appropriate to use, and the Chinese instruction forbids patient data as input. It does not name sibling alternatives, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. It does disclose several constraints, including not being validated for hospital deployment and not being for pre-submission storage, and it warns not to input patient data. However, these are cryptic boolean-style statements rather than clear behavioral consequences, side effects, or call expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and compact, which is good, but it relies on terse flag-like prose and a Chinese phrase without explaining their practical meaning. It is concise but not optimally structured for agent comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema, the description still omits the core purpose and the meaning of the 'disease' parameter. The constraint flags add some context, but the essential information an agent needs to select and call the tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one required parameter, 'disease', with 0% description coverage. The description never mentions 'disease', valid values, formats, or how to supply it, so it provides no help for parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description labels the tool as a 'CDC compatibility alias' but never states what it does, retrieves, or returns. It does not use a clear verb+resource structure and does not help distinguish it from sibling tools like get_collection_method or get_transport_requirement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives. Flags such as 'decision_support_only=true' and 'not_validated_for_hospital_deployment=true' hint at restrictions, but they are not translated into actionable usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It offers metadata flags like 'decision_support_only=true' and 'not_validated_for_hospital_deployment=true', which hint at constraints, but it does not describe what the tool does, what it returns, or what side effects or permissions apply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short but poorly structured: the '=true' flags read like serialized metadata rather than coherent guidance, and the Chinese privacy warning is appended without context. It is not overly long, but the limited space is spent on opaque flags instead of useful tool semantics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even with only one parameter and an output schema, the description omits the core purpose and input semantics, leaving an agent unable to confidently decide whether this is the correct tool among many similar sibling tools. The constraint flags add some context but do not make the definition complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not mention the 'disease' parameter at all. The agent must rely solely on the parameter name, with no information about accepted values, format, or expected input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description never states that this tool retrieves transport requirements for a disease; 'CDC compatibility alias' is an opaque label that does not explain the tool's function. It relies on the tool name for meaning and lacks a clear verb and resource description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus siblings like get_specimen_requirement or get_collection_method. The Chinese instruction '不得輸入病人資料' ('do not input patient data') is a constraint, not a usage scenario, and no alternatives or exclusion conditions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does so thoroughly: it discloses inclusion of cancelled/legacy/uncoded rows, that a blank cancellation field does not imply validity, that no scores/procurement/equivalence advice is returned, that output is raw official text rather than instructions, and that patient data must not be entered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is front-loaded with purpose and every clause adds operational value, but the single dense paragraph in mixed English/Chinese with pseudo-flags is harder to scan than it needs to be. A bulleted structure would improve scannability without cutting content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter search tool with zero annotations, the description is complete: it covers scope, inclusion semantics, ordering vs filtering, pagination, result summary format, and the full-record sibling. The output schema exists, so return-value detail is not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain the parameters; it covers all seven: query implied by 'Search', limit restricted to 1–5, offset for pagination, prefer_* flags as ranking-only, ivd_scope with its four values, and main_category with range A–P as a hard filter. The only minor gap is query syntax, but the search term role is clear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: 'Search all TFDA permit rows, including cancelled, legacy-class and uncoded rows, for any industry.' This clearly scopes the tool as the broad license-row search and distinguishes it from more targeted IVD/search siblings; it also points to get_license for full records.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly separates ordering-only preferences (prefer_ivd, prefer_main_category) from true filters (ivd_scope, main_category) and instructs to apply filters only when the user explicitly wants one category. It gives limit range, offset pagination, and names get_license as the alternative for full fields.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It discloses meaningful safeguards: decision_support_only, verify_current_official_source, not_validated_for_hospital_deployment, not_pre_submission_storage, and 'do not enter patient data'. These are valuable but expressed as cryptic code-like flags that are not explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded with the action. The semicolon-separated flags are compact and relevant, though somewhat cryptic, and there is no filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-format details are covered elsewhere, but the description omits query semantics, when to use this tool versus sibling search tools, and explanations of the boolean flags. These gaps make the tool hard to invoke correctly and confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required string query with no schema description (0% coverage). The description does not explain expected query format, values, or examples; 'do not enter patient data' only adds a constraint, and 'Search CDC rows' only implies free-text searching. This is insufficient compensation for the absent schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Search CDC rows'), and the tool name adds the disease domain. However, 'CDC rows' is somewhat generic and does not name any sibling search tools, so the agent must infer the disease focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use language, no exclusions, and no reference to alternative sibling tools. The only usage-related text is the Chinese warning not to enter patient data, which is a constraint rather than guidance for selecting this tool over alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It clearly states the fixed 5-row behavior, summary-only results, official-source verbatim returns, reviewed-only scope, and deployment/procurement caveats. This is rich, safety-relevant behavioral context beyond a bare search description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but structured, with purpose, constraints, usage guidance, and data-handling warnings each earning their place. It is longer than a minimal description, but the length is justified by the safety and regulatory caveats; slightly repetitive phrasing keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return-value details do not need to be spelled out. The description covers purpose, row limit, summary-only results, source authenticity, and routing to sibling tools. The main gap is the lack of any parameter-usage examples or clarification of what values are valid for query and manufacturer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schemas have 0% description coverage and the tool description never explains what query or manufacturer should contain, what formats are accepted, or how the optional manufacturer interacts with the required query. The parameter names alone provide minimal semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a reviewed-only TFDA compatibility alias of search_reviewed_ivd that returns 5 rows. It states a specific resource and scope, and distinguishes it from the sibling search_reviewed_ivd by the fixed row limit and reviewed-only constraint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly tells the agent when to use alternatives: use search_reviewed_ivd for pagination/more results, and get_license for full fields of a single license number. It also gives explicit no-go constraints such as not for procurement or equivalence, and not to input patient data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that the tool is decision-support only, not validated for hospital deployment, not for procurement or equivalence, that results are summaries only, that 'unknown' has a specific meaning, and that returned content is official data rather than AI instructions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then systematically lists guardrails and caveats. It is dense but each clause adds important safety or usage information. The repeated flag-style statements could be more compact, but they are not wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that an output schema exists, the description need not explain return values, and it covers most operational context: result granularity, limit bounds, alternative for full fields, and meaning of 'unknown'. It is slightly incomplete because it omits offset and manufacturer semantics and does not explicitly distinguish itself from sibling search tools, but overall it is sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaning for limit ('limit 為 1–5') and implicitly for query by prohibiting patient data. However, it does not describe the offset or manufacturer parameters at all, leaving those gaps for the agent to infer from schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Search TFDA IVD candidates (included, ambiguous, unknown) with review coverage.' This clearly identifies the tool's scope. It does not explicitly differentiate it from sibling search tools like search_ivd or search_reviewed_ivd, though it does point to get_license for full license details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage constraints and alternatives: 'limit 為 1–5' for result limits, '完整欄位請用 get_license 查單一許可證字號' for full-field lookup, and strong exclusions such as 'not_for_procurement_or_equivalence=true' and '不得輸入病人資料'. This clearly tells an agent when and how to use the tool, and when not to.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility and does so thoroughly: it discloses fixed top-5 returns, summary-only records, raw official text (not AI instructions), a decision-support-only profile, and invalidity for claims/hospital deployment. This goes well beyond what the name and schema reveal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Most clauses carry useful information, especially routing and safety constraints. However, the description is a dense run-on paragraph mixing pseudo-annotation flags, Chinese, and English, with the jargon opening 'NHI full-table compatibility alias.' It is compact but not well-structured or especially readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a single parameter, no annotations, and an existing output schema, the description covers safety profile, result limits, pagination alternatives, and output nature. The only substantive gap is query parameter semantics, which keeps it from being fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single query parameter has 0% schema coverage, so the description must explain what to put in it. It only adds a negative constraint ('do not enter patient data') and an implied full-table search. It does not state whether query is a lab code, partial match, exact code, or free-text, leaving the agent to guess the accepted input format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening phrase 'NHI full-table compatibility alias' names a resource but never explicitly states the search verb; the tool name carries the core meaning. The rest of the description focuses on constraints, return limits, and alternatives rather than clearly saying 'this tool searches lab codes.' It is not a tautology, but the purpose is mostly inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-not guidance: decision_support_only, not_validated_for_hospital_deployment, not_for_claim_determination, and 'do not enter patient data.' It also names alternatives with conditions: use search_payment_items to paginate beyond 5 results, and use get_payment_rule/get_points for full details. This is strong routing and exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries full responsibility and it does so thoroughly. It discloses the pagination limit, that results contain only summaries, that returned content is raw official data rather than AI instructions, and that patient data must not be entered. This gives an agent substantial operational context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The declaration is compact and front-loaded with the most important constraints and usage rules. Every clause serves a purpose: safety status, pagination behavior, alternative single-item routes, and output semantics. No filler is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, an output schema exists and the description covers the missing operational details: pagination, summary-only results, the correct sibling for full details, and intended/non-intended uses. This is sufficient for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate; it meaningfully explains limit and offset behavior ('搜尋結果一次最多 5 筆' and '要看更多用 offset 翻頁'). The query parameter remains implicit beyond the verb 'Search', so it does not fully document all parameters, but it adds real semantic value over the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Search the current NHI table') and names concrete behavior (returns summary listings). It also differentiates itself from single-item lookups by directing users to get_payment_rule or get_points for full remarks, so an agent can distinguish this search tool from its siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description is explicit about how to use the tool: results are capped at 5, use offset for pagination, and single-item details should go through get_payment_rule or get_points. It also provides context for when NOT to rely on it by declaring it is not validated for hospital deployment and not for claim determination.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and delivers extensive behavioral disclosure: decision_support_only, verify_current_official_source, not_validated_for_hospital_deployment, and not_for_procurement_or_equivalence. It also warns about not inputting patient data, clarifies that each result is only a summary, states the returned content is official source text rather than AI instructions, and prohibits direct use as promotional material.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The tool's purpose is front-loaded and every clause carries distinct value, but the text is a dense block of caveats without visual structure. It is efficient but slightly harder to parse due to the quantity of constraints packed together.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers critical constraints, result granularity, routing logic, and output nature, which is strong for a search tool. However, it omits semantics for three of the four parameters and does not clarify how offset or manufacturer interact with the search, leaving an agent with gaps in execution knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for all parameters, but it only addresses limit (restricting it to 1–5). Query, offset, and manufacturer are left semantically unexplained. Query is central to the tool's function, and its expected format is not described; offset and manufacturer are completely unmentioned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Search'), resource ('TFDA permit rows'), and precise condition ('classification codes were reviewed as IVD (ivd_scope=included)'). This clearly separates it from generic search tools and identifies the exact selection criterion without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit routing instructions: when candidate_matches_available is returned, use search_ivd_candidates; for complete fields, use get_license with a single license number. It also constrains limit to 1–5, clearly stating when and how this tool should be used versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It usefully states that no catalog is returned and 'Show' implies a read-only operation, but it leaves the meaning of 'reserved' ambiguous and does not explicitly state side-effect-free behavior or expected status semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with a clear verb and object, and it includes an important clarifying negative. Every word earns its place, and the key scoping detail ('no catalog is returned') is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read-only status tool with an output schema, this description is nearly sufficient. However, it does not clarify what 'reserved' means or how this tool relates to sibling status tools, leaving a notable gap in when and why the agent should select it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is empty and schema description coverage is 100%, so parameter semantics are already fully handled. With zero parameters, the description needs to add nothing about parameters, and it does not conflict with the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Show') and identifies its resource ('reserved LOINC/FHIR/SNOMED status'), while also adding the useful negative scope 'no catalog is returned.' It is clear about what the tool does, though it does not explicitly differentiate it from sibling status tools like eqa_status or get_data_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives, nor are exclusions or trigger conditions provided. The agent is left to infer when a 'reserved status' check is appropriate, especially among several status-related siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.