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

Annotations already declare destructiveHint=true and idempotentHint=true; the description goes beyond them by specifying exactly what is destroyed — a finished transcript or index is deleted and rebuilt, and the recorded failure is cleared. It also discloses the return value ('the project's analysis status'), which matters since no output schema exists.

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?

Leads with the action and its scope, then the destructive consequence, then the trigger conditions, then the return value — a logical escalation with no filler sentences. Every clause carries information an agent needs.

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 destructive, four-parameter mutation with no output schema, the description covers what it does, what it overwrites, when to reach for it, and what it returns. Prerequisite parameters (token, projectId, mediaRef) are documented in the schema, so nothing essential 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 100% and each of the four parameters is self-documenting, so the schema already does the heavy lifting. The description only adds the mapping of the two kind values to human terms ('picture indexing or speech transcription'); it says nothing extra about mediaRef, projectId, or token handling beyond what the schema states.

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 ('Runs ONE analysis of ONE asset again'), names the two analysis kinds, and scopes the unit of work explicitly ('ONE analysis of ONE asset'). That scoping distinguishes it cleanly from start_transcription and start_visual_indexing, which presumably operate at a broader level.

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?

Gives two concrete trigger conditions: get_media reporting phase 'failed' with a worth-retrying error, or a file whose meaning changed. The word 'again' implies it is not the first-run path, but the sibling tools used for initial analysis (start_transcription, start_visual_indexing) are never named as the alternative, so the routing is inferred rather than stated.

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