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

Without annotations, the description carries full burden. It explains what the tool does (check interactions) and specifies drug name type, but does not disclose how current medications are obtained, whether it returns severity, or any prerequisites like user profile.

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?

Description is concise with one-sentence summary, bulleted use cases, and Args section. Every sentence adds value with no redundancy.

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 tool with one parameter and no output schema, the description covers purpose, usage, and parameter semantics. Lacks output format but not critical given tool simplicity.

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 description must compensate. It adds meaning to the only parameter 'new_drug' by clarifying acceptable names (generic or brand), which goes beyond the schema's bare type string.

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's purpose with a specific verb ('check') and resource ('drug interaction'), and it distinguishes from sibling tools like get_current_medications or get_allergies by focusing on interactions.

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?

Description provides explicit usage scenarios (e.g., when user has a new medication, asks safety, wants interactions), but does not mention when not to use or give alternatives, so it is clear but lacks exclusions.

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 provided, but description fully discloses behavior: no inputs needed, pulls all data automatically. Could mention output format (printable, shareable) but overall transparent.

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?

Description is concise, uses bullet list for clarity, front-loaded with purpose, and every sentence adds value. No superfluous words.

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 output schema, description adequately covers usage. Could mention that the summary is printable or its format, but not necessary for agent to invoke 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?

No parameters in schema, so description doesn't need to add parameter info. Baseline 4 is appropriate as there are no parameters to document.

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 specific verb 'generate' and resource 'health summary' with clear purpose 'sharing with a new doctor'. It distinguishes from sibling tools like get_allergies or get_current_medications by being a complete summary, not a specific data point.

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 lists when to use this tool (e.g., 'health summary', 'document for new doctor') and implicitly when not (for specific queries). No when-not is stated, but the list of use cases is comprehensive and unambiguous.

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 discloses a behavioral constraint ('always call before drug interaction check') and implies read-only behavior. Although it doesn't address permissions or side effects, the tool is inherently low-risk (fetching allergies) and the description suffices.

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 three sentences long, front-loads the purpose in the first sentence, and every sentence adds value. No fluff or repetition.

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 there are no parameters, an output schema exists (though not provided), and the tool is simple retrieval, the description fully covers what the agent needs: what it returns, when to call, and ordering relative to related tools.

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 0 parameters and schema description coverage is 100%, so the baseline is 4. The description does not need to add parameter meaning since there are none, and it correctly avoids redundant information.

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 starts with 'Returns all recorded allergies for the patient' which clearly states the verb ('returns') and the resource ('all recorded allergies for the patient'). It distinguishes itself from siblings like check_drug_interaction by specifying that it provides allergy context before drug interaction checks.

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 explicitly lists when to call this tool: when the user asks about known allergies, drug allergies, or allergic reactions, and states 'Always call this before performing a drug interaction check so allergy context is available.'

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 must disclose behavior. It states that the tool returns only active medications and filters out completed courses. This is transparent and sufficient for a read-only query 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?

The description is only two sentences, front-loaded with purpose and followed by usage guidance. Every word adds value, no redundancy.

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 has no parameters and has an output schema, the description covers all needed context: purpose and usage. It is complete for an agent to select and invoke 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?

The tool has 0 parameters, and schema description coverage is 100%. The description does not need to add parameter details. Baseline for 0 parameters is 4.

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 'Returns all currently active medications for the patient.' This is a specific verb+resource combination. Among siblings, no other tool deals with current medications, so it is well-distinguished.

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 says 'Use this when the user asks what medications they are taking, what drugs they are currently on, or what their current prescriptions are.' It also notes automatic filtering of completed courses. However, it does not mention when not to use or alternatives, but given the tool's simplicity, this is sufficient.

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 provided, so description must disclose behavioral traits. It only states ordering (oldest first) and that it returns a list. No mention of read-only nature, no side effects, authentication, or limitations. Minimal disclosure for a tool with no annotations.

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?

Two sentences; the first gives the core purpose, the second provides usage guidance. No redundancy, every word earns its place.

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?

While an output schema exists, the description omits any context about the marker_name parameter (e.g., expected format, possible values) and does not address potential issues like empty results or pagination. The tool's simplicity partly excuses this, but completeness is insufficient for practical use.

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% for the single parameter 'marker_name'. The description adds no information about what valid values are, format, or examples. The parameter is left entirely undocumented, forcing the agent to guess or rely on context.

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 returns a list of readings for a marker, ordered oldest first. The verb 'returns' and resource 'list of all readings' are specific. While siblings exist, none directly relate to lab trends, so differentiation is implicit but sufficient.

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 lists when to use: 'when the user asks about trends, progress, changes over time, historical readings or whether something is getting better or worse.' Provides clear context but no exclusions or alternative 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 bears full responsibility for behavioral disclosure. It mentions the tool returns data and flags status, but does not address permissions, authentication, rate limits, or any side effects. For a simple read operation this is minimally adequate, but lacks depth.

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 concise: one opening sentence followed by a bulleted list of use cases. Every sentence adds value and is front-loaded with the main action. Zero wasted words.

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 has no parameters and no output schema, the description is complete. It explains what is returned (all recorded vaccinations, with overdue/missing flags) and when to use it. The tool is simple, and the description covers all necessary context for an agent 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?

There are zero parameters in the input schema (schema description coverage 100% trivially). Per guidelines, 0 parameters yields a default baseline of 4. No additional parameter information is needed, and the description does not add any parameter semantics beyond 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 clearly states the tool returns all recorded vaccinations and flags overdue/missing ones, with specific verb 'returns' and resource 'vaccinations'. It distinguishes from sibling tools like get_allergies or get_current_medications by focusing exclusively on vaccination 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 explicitly lists when to use the tool via bullet points (vaccination history, up-to-date queries, missing/overdue vaccines, travel recommendations). No exclusions or alternative tool names are provided, but the context is clear enough for an agent to select it appropriately.

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 disclose behavioral traits. It does not mention that the tool is read-only, what data it returns, whether authentication is needed, or any side effects. The description only lists usage scenarios without behavioral context.

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 concise bullet list of four items with a clear usage instruction at the start. No extraneous text; it is efficient and front-loaded. However, it could benefit from a brief summary sentence.

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 simplicity (one optional param, no annotations, output schema exists), the description provides some usage context but fails to explain parameter semantics or return behavior. It is minimally adequate but leaves gaps in how to use the tool effectively.

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 0% description coverage for the single parameter 'speciality'. The description does not explain what this parameter does, how it filters results, or its allowed values (e.g., whether free-text or expected to match a set of specialties). This is a significant gap for a tool with one optional parameter.

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 lists four specific use cases (doctor visits, specialist notes, medical history by specialty, appointment prep) but does not provide a clear general statement of the tool's purpose. It implies retrieval of visit history, but the verb 'get' is not explicitly paired with a resource definition.

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 explicitly states 'Use this tool when asked about:' followed by four categories, giving clear context for when to invoke it. However, it does not mention when not to use it or suggest alternatives among 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. It mentions that the tool 'Extracts medications, lab results, diagnoses, and allergies automatically using AI,' which discloses the AI extraction behavior. However, it lacks details on auth requirements, error handling, or any potential side effects beyond the extraction.

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 concise with two main sentences and an Args section. It is front-loaded with the primary action and contains no superfluous information.

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 has only one required parameter, no output schema, and sibling tools are all read/analysis tools, the description sufficiently explains the tool's purpose, input, and AI extraction behavior. It does not need to detail return values since no output schema is specified.

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 0% description coverage, but the description includes an 'Args' section for file_path with the explanation 'Absolute path to the PDF or image file to ingest.' This adds meaningful semantics beyond the schema's 'File Path' label.

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 verb 'ingest' and the resource 'health documents (PDF or image)' into the MedMemory database. It distinguishes from sibling tools like check_drug_interaction or generate_health_summary, which are read/analysis tools, not ingestion.

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 explicitly says 'Use this when the user wants to add a prescription, lab report, or any medical document to their health record.' This provides clear context for when to use the tool, though it does not explicitly mention when not to use it or alternatives.

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