operating_metrics

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

With readOnlyHint and openWorldHint already in annotations, the description still adds substantial behavioral context: the proximity-matching mechanism ('proximity-matched numbers near a metric name in free text'), the output being 'not a structured KPI table', the fallback to a 'generic cross-sector list', and an explicit verification directive ('treat every value as a lead to verify against its source URL'). Nothing contradicts the annotations.

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 sentences, each earning its place: (1) scope and sources, (2) parameter tuning plus fallback, (3) quality warning and verification workflow. The core purpose is front-loaded, and there is zero filler or repetition of schema content.

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 two parameters, the description covers the essential ground: what is searched, where, how to narrow it, what happens without narrowing, and how to treat the noisy results. Minor gaps: it doesn't name a specific structured alternative to route to, and the return shape is described only abstractly (proximity-matched numbers with source URLs) rather than concretely.

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 0% at the parameter level, so the description must compensate. It richly explains metricNames — its purpose, how to source the vocabulary (industry_overview/discover_competitors results), and the fallback when omitted. The context object is not explained, but its nested schema provides structural hints for company/sector/country; the gap is minor since metricNames is the differentiating parameter.

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 a specific verb ('Searches for') and a well-scoped resource ('sector-specific operating KPIs'), backed by concrete examples (store count, same-store-sales growth, DAU/MAU, GMV) and explicit sources (investor-presentation and press coverage). This clearly separates it from structured-financial siblings like financial_statements and ratio_analysis without needing the schemas.

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 explicit usage guidance for the key parameter — 'Pass metricNames with the specific KPI vocabulary... for a sharper search' — and discloses the fallback behavior when it is omitted. The noise caveat ('noisier than the server's other tools') implies the agent should prefer structured tools for citable facts, though it stops short of naming a specific alternative sibling.

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