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

With readOnly/idempotent annotations already covering the safety profile, the description adds genuinely new behavior: the full return shape (overview scores, scene/timeline sections, recreation, metadata), the top-level recreation_prompt, and the polling cadence for in-flight analyses. This is context annotations cannot supply.

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?

Three tight sentences, front-loaded with the action and identifier. The enumeration of report sections is long but earns its place given there is no output schema.

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?

With no output schema, the description carries the return-value burden and does so adequately, enumerating the report contents and the polling behavior for unfinished analyses. Nothing needed to invoke or interpret the result 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?

Single required param with 100% schema coverage, so the baseline is 3. The description goes beyond the schema's 'The report id to fetch' by telling the agent where a valid report_id comes from (analyze_video_report or list_vision_reports).

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 (Fetch) and resource (a finished Video Analysis report) and keys it to report_id. It names the sibling tools that produce IDs (analyze_video_report, list_vision_reports), so an agent can distinguish it from those generators without opening a schema.

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?

Clearly scopes usage to finished reports and explains the in-progress case: the tool reports processing and should be polled every 20-30 seconds. It lacks an explicit when-not-to-use statement, but the ID provenance pointer routes the agent to the right siblings.

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