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

Annotations already declare read-only, open-world-false, and idempotent behavior, so the description adds value by specifying the objective scoring basis and explicitly distancing itself from medical advice or recommendation. It does not describe edge cases like sorting order or result limits, but these are minor given the annotation safety profile.

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?

Two sentences with the core purpose and the most important caveat front-loaded. No filler or repetition of schema contents.

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 9-parameter tool with no output schema, the description covers the essential contract: what is ranked, on what criteria, and what it is not. It does not spell out the exact response shape or scoring formula, but 'rank by objective score' is sufficient for a read-only, idempotent query.

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 covers 56% of parameters; the description names scoring factors ('price', 'shared-care') that partially clarify max_price_gbp and needs_shared_care, but limit, for_child, and output ranking semantics are not described. The parameter names are largely self-explanatory, so the description adds modest value beyond the schema.

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?

States a specific verb ('Rank'), a specific resource ('UK ADHD/autism assessment providers'), and the scoring dimensions (price, rating, verification/CQC, wait, shared-care). This clearly differentiates it from siblings like search_providers and get_provider, and the disclaimer clarifies it is not a recommendation.

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 clearly implies this tool is for obtaining a ranked comparison of providers rather than a single provider or a recommendation. It does not explicitly name alternatives or exclusions, but the context is strong enough for an agent to know when to invoke it.

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