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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds valuable behavioral context: it explains the distinction between 'trains' and 'involves', how results are ranked, how muscle-group queries spread results across distinct movements, and how locale affects returned names. This goes beyond what annotations provide, though it doesn't detail pagination or exact result structure.

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 dense but well-organized, front-loading the core purpose and then layering behavioral details. Every sentence adds information, though the length is substantial. It could be slightly more concise, but the detail is relevant and earns its place.

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's complexity (natural-language queries, ranking nuances, locale behavior) and the presence of an output schema, the description covers all the essential context an agent needs to select and invoke the tool correctly. It explains the key behavioral distinctions, usage context, and parameter semantics without needing to describe return values since the output schema exists.

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 documents all three parameters. The description adds meaning by explaining how the `query` parameter handles natural language and how `locale` interacts with translation. It doesn't add much beyond the schema for `limit`, but the added context for query and locale justifies a score above baseline.

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 states a specific verb ('Search') and resource ('exercise catalog'), and immediately clarifies the search dimensions: name, muscle group, or keyword. It also distinguishes itself from getExercise by noting that only `fields: full` carries the full involvement list, which helps an agent differentiate this tool from its siblings.

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 when to use this tool: 'Use when building or modifying templates, or when acting on a recommendation that names a muscle group.' It also provides guidance on natural-language queries and explains ranking behavior, which helps an agent decide when this tool is appropriate versus alternatives like getExercise.

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