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

Beyond the readOnlyHint and idempotentHint annotations, the description adds valuable behavioral detail: no verdict is produced, no recommendation-trail entry is written, the logged shot's own bean and age at pulled_at are used, and shot_id mode ignores metric parameters. These are meaningful specifics that the annotations alone do not provide.

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 front-loaded with the most important constraint ('Sandbox-only diagnosis, writes nothing') and organizes the two modes efficiently. Every clause adds useful detail, and the length is appropriate for a tool with 10 parameters and multiple usage modes.

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 10-parameter tool with an output schema and safe annotations, the description covers side effects, mode selection, parameter interactions, and output-shape expectations. An agent has enough information to select the correct parameters and understand the result without needing additional clarification.

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?

Although schema coverage is 100%, the description adds critical parameter-interaction semantics: shot_id is a dry-run mode that ignores the metric fields, while the full metric set defines a hypothetical shot. It also clarifies sensory_tags override behavior, which goes well beyond the baseline for a well-covered 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?

The description opens with 'Sandbox-only diagnosis' and specifies two concrete modes: dry-run a logged shot or evaluate a hypothetical shot from a full metric set. This clearly distinguishes the tool from diagnose_shot by emphasizing that it writes nothing while returning the same output shape.

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 gives explicit guidance for when to use shot_id versus the full metric set, and explains the optional sensory_tags override. It does not explicitly say 'use diagnose_shot when you want a real, persistent diagnosis,' but the sandbox-only, writes-nothing framing makes the intended context reasonably clear.

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