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

With no annotations, the description carries the full burden. It does disclose the key side effect (writes a file to the local filesystem) and the return value (saved file path), which is the most important behavior for a write tool. However, it says nothing about overwrite behavior, permissions, network/rate-limit constraints, or failure modes.

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 waste, with the action and the source front-loaded and the return value last. Nothing is repeated from 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?

There is no output schema, but the description covers the return value explicitly, and all parameters are fully documented in the schema. For a simple single-file download tool the only real gap is the absence of overwrite/permission 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 description coverage is 100%, including defaults and the 'created if it does not exist' note on save_dir, so the schema already documents all six parameters. The description adds no parameter-level meaning beyond that, which is the baseline-3 case.

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 ('Download an icon's SVG file'), names the source (bioicons.com), and states the effect (save to local filesystem) plus the return value. This is clear enough to distinguish it from the read-only siblings (get_icon, get_icon_info), though it never names an alternative 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 only implied: you use this when you need the SVG persisted to disk rather than fetched into context. No when-to-use/when-not guidance and no mention of when get_icon would be the better choice, so the agent must infer the distinction.

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 the return shape ('SVG source is returned as text') but says nothing about failure behavior when an icon is not found, ambiguity resolution beyond the schema's fallback note, or rate/auth limits. Partial coverage of the behavioral surface.

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 tight sentences, front-loaded with purpose, then invocation rule, then return type. No filler or repetition of the tool name.

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 4-parameter read tool with no annotations and no output schema, the description covers purpose, invocation and return type. It omits error/no-match behavior and disambiguation guidance, leaving gaps an agent might hit in practice.

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 baseline is 3. The description adds genuine value by explaining the either/or resolution strategy — exact name alone, or all four identifying fields together — which is an invocation constraint not spelled out in the schema itself.

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) and resource (SVG content of an icon) with the source named (bioicons.com), which is clear and concrete. It does not, however, differentiate itself from siblings like get_icon_info or download_icon, which an agent could confuse with this one.

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 invocation guidance ('Provide either the exact icon name or all four identifying fields'), which helps the agent know how to supply parameters. It says nothing about when to choose this tool over get_icon_info or download_icon, so alternative selection 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?

No annotations are provided, so the description carries the full burden. It does disclose the return contents (including attribution requirements and the SVG URL), which is genuinely useful because there is no output schema. It says nothing, though, about behavior on a missing icon, whether the optional author/license/category params act as filters or disambiguators, or any permissions/rate limits.

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 front-loaded sentence that packs the verb, resource, and return contents with zero filler. 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?

With no output schema, the description correctly compensates by enumerating the returned metadata fields, which is the most important missing piece. The remaining gap is selection guidance against the closely-related get_icon and download_icon siblings.

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 four parameters are already documented in the schema and the baseline is 3. The description adds only marginal semantic value — the parenthetical '(with full name and URL)' hints that the license field is structured — and does not explain how the optional author/license/category params change the lookup.

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 detailed metadata for a specific icon") and enumerates the exact fields returned, so the agent knows this is a metadata lookup rather than a download. However, it does not distinguish itself from the near-identical sibling get_icon, nor explain how it relates to download_icon, leaving the agent to guess between them.

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 when-to-use guidance, no mention of prerequisites, and no named alternative — despite a sibling named get_icon that appears to serve a very similar purpose. Usage is only implied by the listed return 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 are provided, so the description carries the behavioral burden. 'List all' implies a read-only operation and it discloses returned fields (icon counts and bilingual descriptions), but it omits pagination, ordering, authentication, or rate-limit 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 efficiently structured sentence with no filler. The core action and returned content are front-loaded.

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 read tool with no output schema, the description gives enough context about what is returned. It could be more complete by explaining how the language parameter affects the bilingual descriptions.

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 language enum is already documented. The description mentions English and Chinese descriptions but does not clarify how that relates to the single language parameter, adding little parameter-specific meaning and creating mild ambiguity.

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: list all icon categories available on bioicons.com. It also says what each category includes, making it clearly distinct from sibling tools that fetch, search, or download individual icons.

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 browsing/discovery usage by saying it lists all categories, but it does not explicitly say when to use this instead of search_icons or get_icon. No exclusions or prerequisites 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; it does disclose the returned field set and that filtering is optional, which is useful behavioral context. It omits other traits an agent would want: read-only/safety profile, pagination behavior beyond the limit param, rate limits, and auth requirements. Disclosing the return shape is real value, but the behavioral picture 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?

Three tight sentences, front-loaded with the purpose, then return values, then filters; no filler. Slightly more could be said about routing, but nothing present 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?

For a read-only search tool with no output schema, explaining the returned fields (including the SVG URL) is exactly the missing piece and it is supplied. The schema fully covers the parameters, and the absence of annotations makes the safety/profile omission a modest gap rather than a fatal one.

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 query, limit, license, and category are all documented in the schema itself; the baseline is 3. The description only restates optional category/license filtering and adds no syntax or format detail 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?

States a specific verb (Search) and resource (bioicons.com icon library) scoped to keyword search, and enumerates what comes back (name, category, license, author, SVG URL). It never contrasts against siblings like get_icon or list_categories, so an agent must infer the boundary, but the core purpose is 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?

'Search ... by keyword' plus 'Optionally filter by category and/or license' implies the discovery use case, which is adequate for a search tool. However there is no explicit when-to-use-vs-alternatives guidance (e.g. use this to find icons, then get_icon_info or download_icon), leaving the agent to infer routing among four siblings.

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