Prime Cuts Nursery

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

Annotations already cover read-only and idempotent behavior. The description adds that the article text is pre-filled with business facts, which is a behavioral detail. It does not disclose any side effects, but given the annotations, this is sufficient.

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—two sentences—and front-loaded with the core purpose. It avoids redundancy and includes specific use cases without unnecessary detail.

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 simplicity of the schema (one parameter) and no output schema, the description fully covers what the tool returns and when to use it. It also lists example topics, making it complete for an agent to decide when to invoke 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 parameter 'slug' is fully described in the schema with an example. The tool description does not add any additional meaning about the slug itself, only that it identifies a single article page, which is redundant. Since schema coverage is 100%, a baseline score of 3 is appropriate.

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 defines the tool's function: returning the full text of a single guide/authority/regional page. It lists specific use cases (ordering, delivery, testing, etc.) and distinguishes it from listing/search tools by focusing on one article with pre-filled business facts.

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 when to use the tool ('Use to answer detailed questions about...'), providing clear context. However, it does not explicitly mention alternative tools or give negative usage cases, so it falls short of full explicitness.

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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavior beyond that: outputs are separated into clones and teens, prices differ and must never be summed, and passing 'strain' produces a dated one-sentence summary. No contradiction with annotations exists.

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 status list, and every sentence carries useful information, including the critical 'never add them together' caveat. It is somewhat dense with colon-separated details, but no sentence is 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?

With no output schema, the description fully takes on the burden of explaining return semantics: clones and teens lists, one row per strain, links, and the optional strain-specific summary. The tool has no required parameters, and the optional input behavior is thoroughly described.

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 100% and the single optional 'strain' parameter is already documented as accepting menu slug, encyclopedia slug, or name/alias. The description adds meaning by explaining that passing it returns a dated summary including associated teens, which is useful 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 identifies the operation ('Live stock status for every strain listed on /live-inventory in one call'), the resource, and the status vocabulary (InStock / PreOrder / OutOfStock). It also distinguishes the clones and teens product lines, making it distinguishable from siblings like get_teen_inventory.

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 clear usage context: use this for a full availability snapshot, report both clones and teens when asked, and pass 'strain' for a single-strain summary. It does not explicitly name alternatives or say when not to use this tool, so it stops short of a full 5.

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 already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no further behavioral details, which is acceptable given the annotations are present and no contradiction exists.

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, focused sentence that covers the return content without unnecessary words or repetition. It is well-structured and easy to parse.

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?

There is no output schema, but the description lists the key return components (summary, cultivars, menu strains, collaborators), which sets clear expectations for the response. It lacks error handling or edge-case details, but for a simple get operation this is sufficient.

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 already describes the slug parameter with an example ('capulator'). The description adds no additional context about the parameter, so the schema carries the full semantic load.

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 clearly states it returns a single breeder's summary, all attributed cultivars with type, lineage, and menu status, plus menu strains and collaborators. This distinguishes it from list or search tools that provide overviews.

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 explicit statement about when to use this tool versus alternatives like list_breeders or get_strain. The 'one breeder' phrasing implies it is for retrieving details of a specific breeder, but this is not spelled out.

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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description's content—profile facts, ordering terms, deposit/delivery terms—does not contradict those. The description adds no hidden behavioral surprises, so transparency is adequate with the annotation support.

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 front-loaded sentences cover all essential content, and the list of profile facts is concrete and useful. There is no filler, redundancy, or irrelevant detail.

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 parameterless read-only profile getter with no output schema, the description supplies enough content detail for correct invocation and expected returns. The sibling list shows this is one member of a set, and the description's coverage is sufficiently specific to avoid sending an agent to other 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?

This tool has no parameters, so the description cannot add per-parameter meaning; the 0-param baseline of 4 is appropriate. The field list effectively communicates what will be returned.

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 'Who Prime Cuts Nursery is' and lists concrete content: legal name, contact info, hours, licence, ordering terms, and testing policy summary. This makes the tool's resource and scope clear, but it does not explicitly differentiate it from siblings like get_locations or get_testing_policy.

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 to use it for any question about contacting, visiting, or ordering from the nursery, so an agent has clear invocation context. It does not spell out when NOT to use it or name 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?

Annotations already carry the read-only, idempotent, non-destructive profile, so the description's burden is lower and it adds real context: the call returns the live aggregated view 'as shown on /live-inventory', includes an added forecast and teen section, and mirrors a public page. It doesn't disclose response size or freshness/volatility, but for an aggregate read tool with this annotation set, the behavioral disclosure is well above threshold.

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 key idea is front-loaded ('Everything for sale right now in one call') and each subsequent clause earns its place by naming a distinct content area. The parenthetical is a little dense, but there is no filler or verbosity.

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, no output schema, a minimal input schema, and complete safety annotations, the description adequately covers what the tool returns, where the data comes from, and when to use it. The only notable gap is not guiding agents who only want teens to the get_teen_inventory sibling, which would round out the routing story.

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, so the schema coverage baseline is 4. The description reinforces that the tool is self-contained — 'everything in one call' — which is exactly the parameter semantics an agent needs for a no-input tool.

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 ('everything for sale right now in one call') and enumerates the exact content: fresh rooted clones, talls/clearance, 17-day rooting forecast, clone ordering terms, and teens. It also differentiates from siblings by saying it is 'more detail than get_availability' and clarifying that it subsumes the teen inventory view, so an agent can tell it apart from get_teen_inventory without opening schemas.

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 gives an explicit use case ('Use for what's available?') and identifies one alternative (get_availability) along with its distinguishing feature ('more detail than get_availability'). It does not go the last step of saying when NOT to use it, nor does it explicitly point the agent to get_teen_inventory for the teen-only case, so it stops just short of a 5.

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 already establish readOnly, idempotent, and non-destructive behavior, lowering the burden on the description. The description adds scope context such as California-specific delivery terms and teen delivery fee, but doesn't mention return format or data freshness. No contradiction with 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?

A single concise sentence front-loads the primary content (address and visit policy) and then lists delivery terms and regional pages. Every phrase carries information, with no filler 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?

For a no-parameter, read-only information tool, the description covers the key content areas: location, visit policy, delivery terms, and regional pages. It doesn't promise a specific response structure, but without an output schema the high-level enumeration is likely sufficient. It could be slightly more explicit about whether hours or contact details are included.

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 and schema coverage is 100%, so there is no parameter ambiguity to resolve. Per the 0-params baseline, the description does not need to elaborate on parameters.

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 resource as nursery address, visit policy, California delivery terms, and regional pages, which clarifies what get_locations returns. It lacks an explicit verb, but 'get_locations' plus the content list makes the purpose understandable. It doesn't explicitly distinguish from siblings like get_business or quote_delivery.

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 such as get_business, get_availability, or quote_delivery. The description implies a static reference-info use case but does not state exclusions or preferred conditions.

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 already declare readOnlyHint and idempotentHint, and the description adds that live availability is fetched if sold, which is a useful behavioral detail. No contradictions with 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?

The description is relatively compact but packs in many details. It is structured with a clear list of returned fields and separate sentences for slug types and availability, making it easy to scan without being bloated.

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?

Without an output schema, the description enumerates the expected fields (lineage, terpenes, awards, etc.) and explains the availability sub-object. This gives an agent enough context to anticipate the response, though the exact structure is not 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 parameter slug is fully explained with two accepted formats and concrete examples ('wedding-cake' and 'wedding-cake-cannabis-clones'), going beyond the schema description to clarify 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 clearly states the tool's purpose: returning a full encyclopedia record for a cultivar, including detailed fields like lineage, breeder, terpenes, and effects. It also specifies that live availability is included if the item is sold, leaving no 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 provides concrete input guidance (slug types with examples) and explains when live availability appears, but it does not explicitly compare to sibling tools like search or list_strains. Still, the use case is clear from context.

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?

The description implies a read-only operation by focusing on inventory availability and terms, and the annotations (readOnlyHint, idempotentHint, destructiveHint) reinforce that there are no side effects. No contradictions are present, though explicit mention of being read-only would have been slightly clearer.

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, concise sentence that packs all key information: current availability, upcoming groups by ready date, and ordering terms. There is no redundant or extraneous content, making it well-structured and easy to parse.

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 the description covers the main content (inventory and terms), it does not explain what 'teens' or 'flip' mean, nor does it specify the output format or any additional details like pricing or group sizes. Given the domain-specific nature and lack of an output schema, this leaves some gaps in agent understanding.

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, so the description has no obligation to describe parameter inputs or outputs. The baseline for no parameters is 4, and the description adequately introduces the data it returns without needing to explain missing inputs.

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 that the tool returns live inventory of ready-to-flip teens and upcoming groups by ready date, along with ordering terms. However, it relies on jargon like 'flip' and 'teens' without defining them, which slightly reduces clarity for agents without domain context.

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 does not provide any guidance on when to use this tool versus the many sibling tools (e.g., get_inventory, get_availability, list_strains). It lacks explicit conditions or alternatives, leaving the agent to infer the appropriate context from the name alone.

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 already declare readOnlyHint and idempotentHint, and the description is consistent with those. It adds useful context by indicating that this tool reports policy facts rather than performing tests or mutations, so an agent can predict the tool's 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?

A single tightly packed sentence where every phrase adds a distinct facet: method, pathogens, frequency, positive rate, and buyer visibility. It is front-loaded with the core topic and contains no filler 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?

With zero parameters and no output schema, the description is complete: it tells the agent exactly what data the tool exposes and what to expect. There are no inputs to validate, no side effects to warn about, and no missing prerequisites.

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 zero parameters, so the baseline is 4. The description has no parameter burden and naturally conveys that the tool takes no input and returns a single policy overview.

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 defines what the tool provides: a testing-policy overview covering RT-qPCR method, pathogens, frequency, HLVd positive rate, and buyer availability. This is specific and distinguishes it from sibling getters like get_article or get_inventory, even though it does not literally use the word 'retrieves'.

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 clear context for when to use this tool: when information about the pathogen-testing program is needed. It does not explicitly name alternatives or exclusions, but no sibling tool covers this domain, so the contextual guidance 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?

Annotations already declare readOnly, idempotent, and non-destructive, and the description adds no contradicting side effects. It only says 'Returns...', so it does not add much behavioral context beyond 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 contain the full purpose, kind taxonomy, and output fields without extraneous detail. The structure is easy to scan.

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 lists returned fields, which helps despite no output schema, and explains kind values. It omits important context like limit semantics, default ordering, and how filters combine, making it adequate but not comprehensive.

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?

q is described as a substring match, and kind's enum values are partially explained in the main description, but limit has no description and its semantics must be guessed. Schema coverage is low, and the description does not compensate for the undocumented limit.

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?

Clearly states the tool lists published long-form pages, enumerates the five kinds with examples, and specifies returned fields. It is readily distinguishable from sibling tools like get_article or search.

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 explains what is listed and the kinds, so an agent can infer when to use it. It does not explicitly tell when to prefer it over search or get_article, nor mention filtering behavior beyond the schema.

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 already declare readOnly, idempotent, and non-destructive behavior. The description adds no additional behavioral details beyond the fact that it returns all breeders, which is already obvious from the wording.

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, compact sentence with no redundant information. It efficiently conveys the scope and content of the response.

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 list operation with no parameters, the description provides all necessary context: the exact count (51) and the fields included. No further details are needed.

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 no parameters and the schema coverage is 100%, so the description does not need to explain any inputs. The baseline of 3 applies.

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 that it returns all 51 breeders with specific details, and it distinguishes from siblings like get_breeder (single) and search (query) by indicating the full list.

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 implies it is used when the complete list of breeders is needed, though it does not explicitly contrast with get_breeder or search. The 'All 51 breeders' phrasing makes the use case clear enough.

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 already mark read-only/idempotent/non-destructive; description adds relevant behavior: relevance ranking, no inference beyond documented record, and inclusion of a live-availability menu block when applicable. No contradiction.

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 purposeful: purpose first, then query semantics, then result behavior, with no filler or redundant restatement of the schema.

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?

Complex 15-parameter tool is handled well; description covers query semantics, output highlights (matched_on, menu, live availability), and business context (Prime Cuts). It omits a full result-field list, but that is not needed for selecting and invoking.

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?

Despite 73% schema coverage, description enriches key parameters: q accepts descriptive phrases, flavor treats synonyms (gas/fuel/diesel), yield is a minimum rating, terp_profile_of switches meaning, flowering_max is a cap, and on_menu/exclusive are defined.

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 'Meaning-aware search over the 331-cultivar encyclopedia, ranked by relevance' – a specific verb and resource plus filtering/ranking distinction from siblings like get_strain/search.

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?

Gives concrete query examples and states that free-text q maps to the same meanings as explicit filters; however, it doesn't explicitly contrast when to prefer this over sibling search/get_strain, though the encyclopedia/filter framing makes it inferable.

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?

The description goes well beyond the annotations (readOnlyHint, idempotentHint, etc.) by disclosing the exact pricing algorithm (Google driving round trip × $3/mile under 199 miles, $2/mile at 199+, capped at $1,450), the additional outputs when product+quantity are given (per-plant tier, subtotal, free-delivery qualification, total), and the limitation that it cannot see or book delivery schedules. This level of detail makes the tool's behavior fully transparent and consistent with the read-only annotation. No contradictions.

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-organized block that leads with the core purpose, then explains the pricing formula, then lists optional outputs, then provides usage guidance and a limitation. Every sentence earns its place: no fluff, no repetition, and the most critical information (what it quotes and the calculator) is front-loaded. The structure is dense but easily parseable.

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 complexity (conditional logic, optional product+quantity, no output schema), the description covers everything an agent needs to know to call it correctly and interpret the result: it states the outputs (delivery cost, per-plant tier, subtotal, free-delivery flag, total), the fee-only limitation, and the pickup toggle. The lack of an output schema is compensated by explicitly enumerating the return values. No significant gaps remain.

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 100%, so all parameters are already documented. The description adds meaningful value by clarifying the conditional relationships: destination is required unless pickup=true, and product+quantity are only needed when the user wants additional product pricing. It also explains that setting pickup=true returns a pickup-only price. These insights go beyond the schema's individual property descriptions, improving the agent's ability to construct correct calls.

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: quoting delivery costs to a California address and, when product+quantity are provided, also quoting per-plant tier, subtotal, free-delivery eligibility, and total. The verb 'quote' is specific, the resource is the nursery's pricing calculator, and it distinguishes itself from all sibling tools (which are informational getters like get_availability, get_inventory, etc.) by being the only one that computes pricing. There is no ambiguity about what this tool 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?

The description explicitly directs the agent to use this tool instead of estimating prices or delivery costs itself, and it flags what it cannot do ('Fee-only: it cannot see or book delivery schedules'). It also provides a conditional instruction ('Set pickup=true for a pickup-only price'), clarifying when the pickup parameter should be used. While it doesn't name alternative tools, none of the siblings offer quote functionality, so the guidance is effectively complete.

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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds no extra behavioral context (e.g., rate limits, side effects, or authorization), so it stays at the baseline for tools with annotations covering the safety 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?

The description is concise—two sentences—and includes meaningful examples while avoiding fluff. It efficiently conveys the search scope and the primary use case.

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 simple two-parameter tool, the description provides sufficient context: what is searched (cultivars, breeders, articles), the meaning-aware fields, and when to use it versus list_strains. No critical information 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 input schema covers both parameters with descriptions and examples (e.g., 'gelato', 'seed junky'). Schema description coverage is 100%, and the tool description adds no further parameter details, so baseline score applies.

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 function: a one-call search across cultivars, breeder registry, and published articles. It also explicitly differentiates from list_strains, making the purpose unambiguous.

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 guidance: 'Start here when a user names a strain, breeder or topic and you are not sure of the slug' and directs users to list_strains for ranked, filtered results. This provides clear when-to-use instructions and alternative handling.

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