graph_stats

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

No annotations are provided, so the description carries the burden, but 'summary counts' inherently implies a cheap read-only operation with no side effects and no arguments. It does not state that explicitly, nor does it note whether results reflect index staleness or refresh state, which is the one behavior that could matter here.

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 sentence with the resource front-loaded and the payload spelled out in a compact parenthetical. Every word earns its place and nothing is buried.

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 trivial no-param counter with no output schema, the description covers what will be returned (files, symbols, edges, languages) well enough to call it confidently. It leaves out only whether counts cover the whole index or a scoped subset, and any staleness caveat.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a zero-param tool is 4. The parenthetical list usefully describes output content rather than inputs.

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 resource (the indexed graph) and enumerates exactly what is counted (files, symbols, edges, languages). That distinguishes it from every sibling, which query or traverse rather than summarize. It stops short of a crisp verb like 'Returns', but the intent is unambiguous.

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?

No statement of when to call this versus project_graph or the find_* tools, and no mention of prerequisites such as the index being built first. Usage must be inferred from the word 'summary'. It is only marginally guided by the fact that there are no parameters to misuse.

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