ccg_stats

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

With no annotations, the description carries the full burden, and it does disclose one useful trait: it should be called first as a DB-loaded health check, implying failures when the graph is absent. It does not describe what happens on an unloaded DB, cost/latency, or the response shape.

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?

Three short, front-loaded sentences with no padding: what it counts, the optional grouping mode, and the call-first advice. The "cpp-coro-graph:" prefix is slightly redundant but sets domain context cheaply.

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 zero-required-parameter stats tool with no output schema and no annotations, the description covers the core use and the call-first check. It is still thin on limit semantics and failure behavior, which matter given the absence of structured hints.

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 coverage is 67%; by_namespace and namespace are already documented in the schema, and the description largely restates by_namespace's meaning. The limit parameter has no description in either place, so the description does not compensate for the coverage gap.

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 concrete verb and resource: node/edge counts broken down by kind and device, plus an optional per-namespace mode. It is distinguishable from query/node/callers siblings, but it never clarifies how it differs from the very similar sibling coro_stats.

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?

"Call first to confirm the graph DB is loaded" gives explicit ordering guidance that an agent can act on. However, no condition is given for choosing ccg_stats over coro_stats, so the routing guidance is incomplete.

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