get_experiment_report

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

With no annotations at all, the description carries the full burden and does substantial work: it declares the report is frozen (immutable snapshot), enumerates the semantic guarantees (raw vs canonical status, validation states, error class, caveats), and explicitly states timeouts are never reported as infeasibility. Missing auth/permission requirements and behavior on an unknown run_id keeps it from a 5.

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?

Front-loaded with the verb and resource, then the payload and the id formats. The middle clause is a dense comma-list of return fields, which is information-rich but reads as a run-on; it could be trimmed given an output schema already exists.

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 single-parameter read tool with an output schema, the description covers the input format thoroughly and adds semantic guarantees. The enumerated return fields overlap with what the output schema presumably declares, and invalid-run_id behavior is unstated, but nothing essential for a correct call 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?

Schema coverage is 0% (run_id has no description), so the description must compensate, and it does: three run_id shapes are given with concrete examples ('<experiment>/<record>', 'ND-SEED-<seed>', 'MOCK-*'). This is more than the schema provides and enough to construct a valid argument.

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?

States a specific verb and resource ("Read a frozen experiment/run report") and the word "frozen" implicitly separates it from live-status siblings like get_plan_status. It does not name a sibling explicitly, so an agent must infer the boundary rather than being told.

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?

Usage is implied by "read a frozen report" and the enumerated run_id forms, but there is no explicit statement of when to prefer this over get_plan_status, list_tasks or get_task_info. The agent gets context but no exclusions or routing rule.

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