flutter_source_search

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

No annotations are provided, so the description carries the burden. It discloses that the search is over 'pinned at the exact versions the sample corpus was verified against' (version context) and 'vendored ground-truth' (source of truth), which is useful. However, it doesn't disclose regex case-insensitivity behavior, result-count caps, or search scope limits beyond package restriction — though the schema documents these parameters. It doesn't contradict any annotations (none exist), and adds version-pinning context beyond schema.

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 substantial paragraph that packs useful context: the search domain, the pinning, and concrete use cases. It's front-loaded with the verb and resource. It is slightly dense but every clause earns its place — the examples of search terms and question types add genuine value. Could arguably be trimmed, but nothing 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?

Given no annotations and no output schema, the description does solid work: it scopes the source of truth (vendored, pinned versions, specific federated packages), explains when to use it, and hints at result behavior (matched lines via max_results cap). For a grep/search tool with fully documented parameters in the schema, this is reasonably complete. It could mention return format (matching lines + context), but with max_results documented, the essential behavior is conveyed.

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 documents all 3 parameters (query, package, max_results). The description adds some value by explaining the semantics of what's being searched (regex/fragment examples like 'GATT_ERROR|status 133'), which enriches the query param meaning beyond the schema's terse description. However, it doesn't add meaning for package or max_results beyond the schema. With high coverage, baseline 3 is appropriate with modest credit for the query examples.

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 ('grep') and specific resource ('vendored ground-truth source of flutter_reactive_ble and its federation'), pinning exact versions. It clearly identifies the tool as a code-search tool over source, distinguishing it from siblings like flutter_docs, dart_docs (reference docs) and flutter_source_read (likely file reading). It also gives concrete examples of what questions it answers (what a call throws, GATT status mapping, method channel contents).

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: 'Use when the answer lives in the implementation' — giving three concrete scenarios. While it names the alternative class of tools implicit in siblings (docs), it doesn't explicitly name a sibling to use instead for non-implementation questions. Given sibling names like flutter_docs/flutter_get_sample exist, a direct exclusion would have earned a 5, but the when-to-use guidance is clear and actionable.

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