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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds significant behavioral context beyond that: it specifies the return structure (composite + sub-scores), notes that 'imagery is always null' and instructs not to treat it as a domain score. This adds value by clarifying data semantics and a critical caveat. Slight deduction because it does not mention pagination or sorting behavior, but the core is well covered.

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 two sentences with no filler. It front-loads the core purpose, then details the return fields and a crucial caveat. Every sentence earns its place; it is as concise as possible while conveying essential information.

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?

While the description covers output and a special constraint, it omits explanation of the two parameters, which are optional but still affect behavior (e.g., limit). Since there is no output schema and schema coverage is zero, the description should at least hint at parameter usage. The 'most recent' wording implies ordering but does not detail limit semantics. This leaves gaps for an agent to correctly call the tool.

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 0%, and the description does not mention either parameter ('limit' or 'theatre_slug'). While 'theatre' is implied, the exact parameter names and their semantics (e.g., meaning of limit, enum values) are absent. With zero schema coverage, the description carries the full burden and fails to compensate, leaving the agent to infer parameter purpose from the schema alone.

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 a specific action ('Most recent posture_scores rows') and a resource ('posture_scores') with a scope ('per theatre'). It also details what is returned (composite + sub-scores) and explicitly warns that 'imagery' is not a domain score, which prevents misinterpretation. This distinguishes it from sibling query tools that focus on different data domains.

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 usage context (when you need posture scores per theatre) but does not explicitly contrast with sibling tools or provide when-not-to-use guidance. Since siblings are distinct query tools, the absence of explicit alternatives is acceptable, but a clear 'use this for posture data' would be stronger. There are no exclusions or alternative routing.

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