can-i-use

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

The description goes beyond the annotations by explaining the resolution behavior for loose names, the exact outputs returned (earliest continuously-supported version per browser, global usage percentage, safe_to_use flag), and the conservative nature of the flag. This gives the agent a solid mental model of what will happen without needing to invoke the 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 compact and front-loaded with the core question, then provides concrete examples and output details, and ends with a clear usage directive. Every sentence contributes useful information without 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 single-parameter, read-only tool with a full output schema and strong annotations, the description is complete. It covers what the tool does, how the input is interpreted, what outputs to expect, and when to use it, so an agent can select and invoke it correctly with minimal uncertainty.

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 provides 100% coverage for the single parameter, explaining that it accepts a feature name or caniuse id and that loose names are resolved. The description adds extra examples like ':has()' and 'container queries', but these largely reinforce the schema rather than introducing meaningfully new semantics.

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

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

The description clearly states the tool's function: it accepts a loose feature name, resolves it to a caniuse feature, and returns browser support versions, usage percentage, and a safe_to_use flag. This is specific and differentiates from siblings like search_features and get_feature_by_id, as it answers the full support question directly.

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 first; it answers the whole question in one call,' giving clear priority and context for when this tool is appropriate. It does not explicitly state when to choose get_feature_by_id or search_features instead, but the guidance strongly implies this tool is the primary entry point for feature-support questions.

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 cover the safety profile (readOnlyHint, idempotentHint, non-destructive), lowering the burden. The description adds genuine behavioral context beyond the schema and annotations: exact-match-only semantics, no fuzzy matching, and that the tool serves as a 'support table' lookup.

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, each earning its place: core purpose, usage condition, and exclusionary behavior. The most decision-relevant information is front-loaded, and there is zero 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 single-parameter lookup tool with a rich annotation set and an output schema, nothing essential is missing. The description covers what the tool does, when to use it, and how it differs from the sibling search tool; the output schema eliminates the need for return-value documentation.

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 schema already documents the single 'id' parameter with a concrete example ('css-has'). The description reinforces that the id must be exact and known in advance but adds no formatting or syntax detail beyond what the schema provides, so 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 states a specific resource (caniuse feature) and the lookup-by-id operation, and explicitly distinguishes itself from siblings by declaring 'No fuzzy matching is applied.' It is immediately clear this is the exact-ID retrieval tool versus a general 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?

'Use when the id is already known, for example from a previous search' gives a clear, actionable condition for when to invoke this tool. The 'No fuzzy matching' statement implies the alternative (search_features) for fuzzy lookup, though it never names the sibling explicitly or states a formal when-not-to-use.

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 read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral context: it is meant for loose, ambiguous queries and likely presents candidates to choose from rather than performing support validation. This goes beyond what the annotations alone convey.

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 two concise sentences with the primary purpose first and usage guidance second. Every sentence earns its place; there is no fluff or repetition of schema content.

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

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

For a single-parameter, read-only, idempotent tool with an output schema available, the description adequately explains when and how to use it. Nothing critical is missing for an agent to select and 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?

The schema already provides 100% parameter description coverage for q, including examples like 'grid' and 'web share'. The description reinforces that the parameter is a loose query but does not add significant new 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 states a specific verb ('Find'), a clear resource ('caniuse feature id'), and a distinctive mode ('loose query'). It distinguishes from the sibling tools by emphasizing ambiguity, candidate selection, and pre-support-lookup 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 gives an explicit usage condition: use this when a query is ambiguous and candidates need to be chosen before checking support. This also implies when not to use it (unambiguous queries or direct support checks), and the phrase 'before checking support' points toward the sibling check_feature_support.

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