architecture_map

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

There are no annotations, so the description alone must disclose behavioral traits. It states that the computation is deterministic and that no generated labels are returned, which is useful and non-obvious context, but it does not clarify side effects, output shape, pagination behavior, or 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?

The description is a compact two-sentence fragment, front-loading the main computation result and adding a useful behavioral disclaimer. It is scannable and contains little waste, though it could briefly address a few parameters or output format.

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 six optional parameters, no annotations, no output schema, and low schema coverage, the description leaves many operational details undetermined. An agent can call the tool with defaults but cannot confidently interpret complex pagination and parameter interactions from the given context.

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 only 17%, and the description contributes almost no parameter-level meaning. It does not explain the two offset fields, component_depth, max_communities, or max_files_per_community, leaving ambiguity especially around offset vs file_offset.

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 specific output ('deterministic file communities'), a data source ('call + dependency graph'), and the kind of metrics returned (internal/boundary edge counts and call-graph hubs). It does not use an explicit verb or clearly distinguish itself from sibling tools like hubs or coverage_map, but the core purpose is inferable.

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 no explicit guidance about when to choose this tool over siblings, no prerequisites, and no 'do not use when' conditions. The intended use case is implied from 'file communities over the call + dependency graph,' but an agent is left to infer it without sibling differentiation.

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