Family Fishin Website Discovery

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 it does so well for the safety dimension: 'strictly read-only and cannot edit content, access admin data, use carts, or place orders' explicitly bounds what the tool will and won't touch. It does not mention pagination, result-size limits, or rate constraints, leaving minor 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?

Two sentences, front-loaded with the core capability and scope, then immediately the constraint. No filler or redundancy; every clause 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?

For a 3-parameter discovery tool with no output schema and no annotations, the description covers purpose, both modes, and the read-only boundary. It does not describe the shape or volume of returned results beyond the no-query case, which is a minor omission given there is no output schema to fall back on.

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 the schema already documents query, include, and limit_per_type. The description's note that omitting the query returns recently modified content largely restates the schema's own query description, adding little beyond the structured fields. Baseline 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 gives a specific verb+resource ('Search or browse the entire public Family Fishin website') and enumerates the covered content types (articles, WordPress pages, WooCommerce products). It distinguishes the tool as the broad site-wide option, but it never names the narrower siblings (search_articles, get_article, etc.), so the differentiation is implicit rather than explicit.

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 clarifies both invocation modes ('Search or browse' vs. 'With no query, returns recently modified public content'), which gives useful context for the query parameter. However, it offers no guidance on when to prefer this over the five sibling search/get tools, and no exclusions beyond the read-only note.

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. It usefully discloses that only public articles are reachable and that output is cleaned plain text with canonical metadata, but says nothing about behavior for missing/invalid IDs, rate limits, or draft/private handling.

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 short sentences, zero waste, with the core action and identifier forms front-loaded before the return-value note.

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 read tool with no output schema, the description covers the return shape (plain text plus metadata) and the public-access constraint. It is close to complete, missing only behavior on misses or unpublished content.

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% and the single parameter is fully documented in the schema, so the baseline is 3. The description's 'by numeric ID or slug' merely echoes the schema's own description rather than adding new syntax or format constraints.

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?

Specific verb + resource: 'Fetch one public Family Fishin WordPress article by numeric ID or slug.' The singular resource and 'public' qualifier distinguish it from search_articles and from get_product/get_site_page, though no sibling is named explicitly.

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?

Usage is implied (retrieve a single known article when you already have its ID or slug), but there is no explicit when-to-use statement and no routing to search_articles for discovering IDs, nor a stated alternative for other content types.

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 present, the description carries the full burden; it does disclose a meaningful behavioral trait — that it returns evidence gaps and refuses to generate unsupported advice. It says nothing about latency, permissions, how many passages come back, or what the 'evidence gap' output looks like, so the disclosure is partial.

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 short sentences, front-loaded with what is returned and followed by the boundary condition. Every clause carries information; no filler or restated naming.

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, so the description should clarify return shape — it does so at a high level ('passages and evidence gaps') without describing structure, and it omits any explanation of the limit parameter. Adequate to attempt a call, but incomplete for using the results well.

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, and it does not. The 'question' parameter's 500-character limit is never mentioned, and the 'limit' parameter (1-10, default 5) — which controls how many passages are returned — is entirely unexplained, leaving the agent to guess its meaning from the name alone.

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 ('Return') and a specific resource ('source-grounded passages and evidence gaps') for a fishing question, and adds a negative scope boundary ('Does not generate unsupported fishing advice'). It does not, however, differentiate itself from the sibling search_fishing_knowledge, which an agent could easily confuse with it.

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 clause 'Does not generate unsupported fishing advice' implies the tool is for evidence retrieval rather than advice, which gives some usage signal. But there is no explicit when-to-use/when-not or any routing to siblings such as search_fishing_knowledge or search_articles, leaving the choice to inference.

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 add that the tool is read-only and that it directs purchases elsewhere, which is genuinely useful. However, it says nothing about error behavior for an unknown ID/slug, authentication needs for non-public data, or latency/pagination concerns.

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 tight sentences, front-loaded with the fetch/keying semantics and followed by the read-only statement. No filler or repetition of the title.

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 compensates well by enumerating what is returned (description, prices, availability, images, attributes, variations, option-plugin fields). It falls just short of complete because it omits failure modes such as an unknown slug and whether unpublished products are excluded beyond the word 'public'.

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 parameter is fully documented in the schema, including an example slug. The description only echoes 'by numeric ID or slug' without adding format or resolution rules, so the baseline 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?

States a specific verb (Fetch), resource (one public Family Fishin product), and keying method (numeric ID or slug), and enumerates the returned content so the agent knows what it gets. It is clearly distinguishable from the sibling search_products, which implies a list-oriented query rather than a single-record fetch.

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 when to use it (looking up a single known product by ID or slug) and notes that purchases are directed to the product page, but it never explicitly contrasts this with search_products or states any preconditions. Usage is inferable rather than stated.

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 and does reasonable work: it declares the tool 'strictly read-only' and states it cannot access drafts or admin pages or edit content, which is the key safety boundary for a fetch tool. It omits auth requirements, rate limits, and error behavior, so it is not fully 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?

Three short sentences with no filler, and the core action (fetch a published page) is front-loaded ahead of the return-value and constraint details. Every sentence contributes new 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?

For a single-parameter read tool with no output schema, the description covers the essentials: what is fetched, what is returned ('cleaned plain text and canonical metadata'), and what is off-limits. Only error/edge behavior (e.g., what happens for an unpublished slug) is unaddressed.

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%, so id_or_slug is already documented in the schema; the description only adds the qualifier that the page must be published and public, which slightly constrains valid values. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Fetch one published public WordPress page') and scopes it clearly to published, public content. It references discover_site as the discovery sibling, though it never explicitly distinguishes itself from get_article or get_product, so an agent must infer the page/article/product split.

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 phrase 'discovered by discover_site' implies the tool belongs in a discover-then-fetch flow, which is useful implied guidance. However, there is no explicit when-to-use/when-not statement and no named alternative for fetching articles or products, so routing between the three sibling fetchers is left to inference.

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 and does real work: it discloses that only published articles are returned, that results are ranked summaries with IDs and canonical URLs rather than full content, and that citation requires a follow-up read. It omits auth requirements, result-count behavior on empty queries, and pagination beyond the limit parameter.

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, zero filler, with the core capability front-loaded and the follow-up instruction second. Nothing repeats the name or title verbatim.

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 two-parameter read tool with no output schema, the description covers purpose, return shape, and the citation workflow adequately. The one gap is its relationship to the closely related search_fishing_knowledge sibling, which an agent must guess between.

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%, so the baseline is 3, but the description adds meaning the schema lacks: the query accepts a natural-language question, not just keyword strings as the schema example ('trout current') suggests. The limit parameter is left entirely to 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?

States a specific verb (find), a specific resource (published Family Fishin fishing articles), and the two accepted query modes (topic or natural-language question). It is clearly distinguishable from get_article, which it names as the follow-up for full text.

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 routes the agent: search here first, then 'call get_article to read a full article before citing it' — a concrete when-to-use-next rule. It does not address when to prefer the sibling search_fishing_knowledge over this tool, leaving the main ambiguity unresolved.

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 burden. It does disclose the return nature (passages plus canonical citations, no synthesized advice), which is genuinely useful. However, it says nothing about read-only behavior, result ordering, or how many passages come back relative to the limit parameter.

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, both earning their place, with the core action stated first and the output contract immediately after. No filler or restatement of the title.

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 two-parameter retrieval tool with no output schema, the description is nearly complete: it covers what comes back (evidence and citations) and that answers are not generated. The only real gap is the undocumented limit parameter and result-count behavior.

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 50% — 'question' is documented, 'limit' is not. The description reinforces that the question must be natural-language free text (adding meaning beyond the bare schema text), but it never mentions the limit parameter or its 1–10 default-5 range, leaving half the parameters unexplained in both places.

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 (find source passages) and narrows the domain to natural-language freshwater fishing questions. The clause 'Returns evidence and canonical citations, not generated advice' implicitly distinguishes it from get_fishing_guidance and search_articles, so an agent can pick between them 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?

Clearly signals the use case: answer factual fishing questions with cited evidence rather than advice. The 'not generated advice' contrast effectively routes the agent away from advice-generating siblings, but no sibling is named explicitly and no when-not conditions (e.g., product lookups, article discovery) are stated.

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 and does well: it declares read-only behavior, rules out ordering ('cannot place orders'), and discloses what comes back (product details and product-page links). It stops short of covering match behavior (exact vs fuzzy), result ordering, or what an empty result means, which matters for a search 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?

Two sentences, front-loaded with the search scope before the sibling routing hint. No repetition of schema fields and 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?

For a two-parameter read-only search with no output schema, the definition covers scope, searchable facets, return contents, and the escalation path to get_product. Nothing essential to invoking it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning by enumerating what the free-text query can target (product name, lure type, color, size, fishing use) rather than only mirroring the schema's single example.

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?

Specific verb ('Find') plus a precisely scoped resource ('public Family Fishin tackle') and an enumeration of the searchable facets. It also separates itself from the sibling get_product by stating the latter is for full options and availability.

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 routes the agent: use this for discovery by name/lure/color/size/use, and call get_product when full options and current availability are needed. The 'public' qualifier also implies private/unpublished items are out of scope, so the when-not condition is inferable from stated scope.

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