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

The description goes well beyond the annotations by disclosing exact non-obvious behaviors: no verdict is produced, no recommendation-trail entry is written, sensory_tags can override stored tags, and the shot's own bean and pulled_at age are used. This is rich behavioral context beyond the readOnly and idempotent hints.

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 well-structured, front-loaded with the most important fact ('Sandbox-only diagnosis, writes nothing'), and every sentence adds information. The two modes are presented clearly without unnecessary verbosity.

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 tool with 10 parameters, no required fields, a full output schema, and safety annotations, the description covers everything needed to invoke it correctly: both modes, ignored params, side effects, and the relationship to diagnose_shot. No critical operational detail is missing.

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?

The schema already covers all parameters at 100%, so the baseline is 3. The description adds value by grouping parameters into two meaningful modes, clarifying that shot_id ignores the metric params, and explaining the sensory_tags override semantics. This is helpful but not strictly necessary given the schema descriptions.

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 names a specific operation ('Sandbox-only diagnosis'), explicitly states it writes nothing, and differentiates it from the sibling diagnose_shot by noting the identical output shape but no verdict or recommendation-trail entry. The two call modes are clearly described, so an agent can tell exactly what this tool does.

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 clear context for when to use the tool: preview a logged shot via shot_id or a hypothetical shot via the full metric set. It implies this is the safe, side-effect-free alternative to diagnose_shot, but it does not explicitly say 'use diagnose_shot when you want actual diagnosis/writes,' so the exclusion is not fully stated.

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