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

Annotations already establish readOnly, idempotent, and non-destructive behavior, so the description's main added value is clarifying that results are paths only and that no file content is returned. It does not describe pagination behavior or response shape beyond that, which keeps it at a moderate score.

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 with no filler; the primary use case, output type, and content boundary are all stated efficiently. It is front-loaded and every sentence contributes useful guidance.

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 glob-listing tool, the description plus fully documented schema cover the main agent needs: what it lists, what it does not return, and when to use it. There is no output schema, so the brief 'returns file paths' statement is adequate, though pagination details are left to the continuation_token parameter description.

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 structured schema already documents every parameter. The description adds general context about glob matching and file discovery, but does not meaningfully expand on any individual parameter's meaning or format.

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 action ('discover files'), the resource ('app's source snapshot'), and the result ('file paths matching a glob pattern, no content'). It also distinguishes itself from content-returning tools by explicitly saying it returns no content, so an agent can separate it from src_read and src_grep.

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?

Opens with 'Use this when you need to discover files' and frames it as a pre-step 'before reading or searching files.' It does not explicitly name sibling tools or state when not to use it, but the content restriction and project-structure use case make the intended context clear.

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