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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that the numbers come from the same underlying rows as the companies endpoint (useful for consistency reasoning) and that no parameters are accepted, but it says nothing about filtering, freshness, or whether counts respect any server-side defaults — leaving a real ambiguity about whether these are totals over the whole dataset.

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 sentences, front-loaded with what is returned and immediately followed by the data provenance and the no-parameter fact. Nothing is padded or repeated.

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 simple parameterless read, the description covers scope (three count dimensions), provenance, and the absence of inputs. Without an output schema, a brief note on the response shape or whether counts are dataset-wide would have closed the remaining gap.

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?

Zero-parameter tool, so the baseline is 4; the description's 'Takes no parameters' simply reinforces the empty schema rather than adding new semantics. No parameters exist whose meaning could be enriched.

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?

Concretely names the aggregation dimensions (stage, industry, source) and ties them to the companies dataset, so the resource is identifiable even though the word 'companies' only appears via the endpoint reference. It does not distinguish itself from siblings like list_companies or get_landscape, which is the only thing keeping it from a 5.

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 phrase 'Computed from the same rows /api/v1/companies returns' implies this is the aggregation shortcut instead of listing companies and counting client-side, which is a useful implicit cue. However, there is no explicit when-to-use statement, no exclusions, and no acknowledgement of when get_landscape or get_market_map would be the better choice.

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