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

The description adds value beyond annotations by stating all values 'trace to plan sources; no synthetic scores' and describing the output as a 'full provenanced record plus dataset-derived indicators'. This addresses data provenance and reliability. Annotations already mark it as read-only and idempotent, so the description complements rather than repeats.

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 a single, information-dense sentence that front-loads the core action and output. Every part is essential: query parameter, resource scope, indicators included, and data provenance. There is no wasted text.

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?

With two parameters, no output schema, and annotations present, the description adequately explains the output content and parameter usage. It covers what data is returned (provenanced records, indicators) and how to use the `section` parameter. Minor omission: no mention of behavior for invalid slugs, but overall complete for the tool's complexity.

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 50% because the required 'slug' parameter lacks a description in the schema. The description provides context by calling it a 'vendor slug' in the first sentence. For 'section', it adds meaning by explaining its purpose and how to obtain valid slugs. However, it does not fully compensate for the missing schema description on 'slug'.

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 returns a 'per-vendor benchmark card by slug within any theme' and lists specific indicators (entry price, normalized cost at 100 and 500 calls/mo, billing models, etc.). It distinguishes from sibling tools by focusing on a single vendor's detailed record rather than comparisons or lists.

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 instructs to set `section` to a theme slug from list_sections, providing default context. It mentions that section defaults to 'ai-receptionists' and directs to list_sections for full slug list. However, it does not explicitly state when to use this tool versus alternatives like compare or find_best.

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