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

With no annotations, the description carries the burden. It states returns 'employer cost and total charges' but lacks details on side effects, permissions, or defaults. The input inconsistency (status parameter not in schema) undermines reliability. Adequate but not thorough.

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 short (3 sentences) and front-loaded, but the inaccurate input listing reduces efficiency. It earns its place but the error wastes the agent's trust.

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 tool with output schema, the description covers purpose, usage, returns, and related tools. But the input mismatch and missing detail on the status parameter mean it is not fully complete. The lack of annotations also limits behavioral context.

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 100% for the only parameter 'gross_monthly', so baseline is 3. However, the description adds 'status (cadre/non-cadre)' which is not a valid parameter, causing confusion. It does not add useful meaning beyond the schema and introduces misinformation.

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 it computes total employer cost in France, giving a specific verb and resource. It differentiates from many sibling calculators by specifying France. However, it mentions an input 'status (cadre/non-cadre)' that is not in the schema, slightly reducing clarity.

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 explicitly says 'Use for hiring budget or freelance vs salary comparison', providing clear context. It also directs to 'list_bundles' for related calculators, guiding exploration of alternatives. No explicit when-not-to-use, but the guidance is solid.

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