findings

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

No annotations are provided, so the description carries the behavioral burden, and it does disclose the kinds of results returned and that filtering is supported. However, it says nothing about read-only nature, result volume/default limit behavior, ordering, or whether findings are cached/stale relative to the index.

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, dense sentence with the enumerations front-loaded and no filler. Slightly list-heavy, but every term 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?

An output schema exists, so return-value explanation is not required. Still, for a 3-parameter tool with zero schema descriptions, the description leaves 'limit' undocumented and offers no usage routing against sibling tools, which is a meaningful gap.

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% for all three parameters, so the description must compensate. It clarifies that 'code' is a prefix match (a real semantic addition) and that 'path' is a filter, but it entirely omits the 'limit' parameter and its default of 100.

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 names a concrete resource (static findings from the index) and enumerates the specific finding categories (TAG_TODO/TAG_FIXME/TAG_BUG, EMPTY_CATCH, SWALLOWED_EXCEPTION, BARE_EXCEPT), which lets an agent distinguish it from grep or find_symbols. It stops short of a full verb framing and does not explicitly say how it differs from the sibling grep tool.

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?

'Filter by code prefix or path' implies the two filtering modes, but there is no guidance on when to prefer this over grep (raw text search) or programming_patterns. The agent must infer that this returns pre-indexed static-analysis findings rather than arbitrary matches.

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