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

With no annotations, the description carries the full behavioral burden and meets it: it discloses that figures are computed live, that Capability Link/Signature counts are active records only, that retired records are excluded, that the active/retired splits live in the capability tools' metadata, and that the secondary-industry breakdown is full-tier only. This gives an agent an accurate model of what the call will and will not report.

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 dense and front-loaded with the verb and primary object, and every clause carries distinct information rather than filler. It is, however, one long em-dash-heavy run-on that could be easier to parse if the enumerated output dimensions were structured; still, nothing is wasted.

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?

Given no output schema and high conceptual complexity, the description is thorough: it enumerates the full set of returned statistics, the derived layers, the special ENT/Warmth Engine Ratio value, the event-ID range, the methodology version, plus exclusions and caveats. An agent can invoke the tool and interpret the response without needing additional documentation.

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?

There are zero parameters and schema coverage is 100%, so the baseline is 4. The description adds a behavioral clarification—'No parameters; figures are computed live'—which reinforces that invocation requires no input, but there is no parameter meaning to elaborate on.

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 opens with the specific verb 'Retrieve' and names an unambiguous resource: 'current corpus statistics' with live counts and distributions. It enumerates the exact dimensions and derived layers (Threads, Capability Links, Capability Signatures, ENT statistics, event-ID range, methodology version), which makes it unmistakably distinct from the sibling entity-retrieval tools even without naming them.

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 implies its own use case—a live overview of corpus coverage—by describing what it returns, but it never explicitly states when to choose it over siblings like get_metrics or get_methodology. The only alternative-reference is the pointer to the two capability tools' metadata for active/retired splits, which is a helpful nuance but not a general usage rule.

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