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

The description goes beyond the annotations by explaining that eligibility results are indicative, not official, and by detailing the meaning of 'potentially_eligible' and the limitations around workforce, company-age, size-text, and fine-grained geographic criteria. It also notes that very local schemes can be omitted. This gives the agent an accurate mental model of the tool's output reliability and edge cases.

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 well-structured with the core purpose front-loaded, followed by clearly labeled Use when, Avoid when, Limitations, and Price sections. Each segment provides necessary decision-making information without redundancy. The length is justified by the rich selection and limitation context.

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 the tool has an output schema and covers a complex domain, the description is complete: it explains purpose, usage boundaries, result interpretation, limitations, and cost. An agent has enough information to select, invoke, and correctly interpret the result of this tool without significant gaps.

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 100%, so the schema already fully documents all three parameters: limit, project, and identifier. The description adds contextual meaning around 'profile, location and project' and hints at how criteria are matched, but it does not add parameter-level details beyond the schema. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 and resource: 'Finds and ranks French public funding programs potentially relevant to a company based on its profile, location and project.' It clearly differentiates the tool from general company data or procurement siblings by focusing on public Aides-entreprises funding programs. The 'Avoid when' clause further clarifies the boundary, making the tool's purpose unmistakable.

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 provides explicit 'Use when' and 'Avoid when' guidance, naming concrete scenarios such as needing explainable matching reasons and known/unknown eligibility criteria, versus needing official eligibility decisions or automatic grant applications. This is strong routing guidance that helps an agent decide when to invoke this tool versus other options.

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