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

With no annotations provided, the description discloses key behaviors: data source (Velarion's canonical_metrics), no LLM narrative invention, data-based summary only, max limit, and exclusion handling. This is sufficient for a non-destructive tool.

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?

Four sentences, each providing unique value: purpose, data source, behavior constraints, and limitations. No wasted words, front-loaded with the core function.

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?

An output schema exists but is not shown; the description compensates by describing the output (ranked table, data-based summary). It covers key limitations but leaves agent_token and fiscal_year unexplained, which is a minor gap given the tool's simplicity.

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 0%, so the description should compensate. It only adds the max 20 constraint for tickers but does not explain agent_token or fiscal_year. The meaning of tickers as company tickers is implicit but not explicitly stated.

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 clearly states the tool compares multiple companies on pay, performance, and governance metrics, which distinguishes it from siblings like benchmark_executive_pay (single metric) and lookup_company_compensation (single company). The verb 'compare' and resource 'companies' are specific.

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 when to use (comparing companies on multiple metrics) and gives constraints (max 20 tickers, out-of-coverage excluded). However, it does not explicitly say when not to use it or compare against alternatives like benchmark_executive_pay.

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