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

Goes beyond the destructiveHint=true annotation by scoping the blast radius: no new project or video segment is created, but automatically generated slides are not recreated — which is exactly the destructive consequence an agent needs to warn about. It does not say what happens to any pre-existing narration on that segment or note performance/cost, so it stops short of full disclosure.

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?

Four tight sentences ordered by importance: purpose, triggering condition, argument provenance, blast radius, then the user-consent gate. No filler and nothing is buried.

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, non-idempotent retry tool with a rich output schema, the description covers trigger condition, required inputs and their source, side effects, and the consent policy. Return values are covered by the output schema, so nothing material 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 description coverage is 100%, so all three params (including the language fallback rule and its pattern) are already documented. The description's 'use exactly the UIDs returned by that operation' adds a useful provenance constraint but largely restates the schema's uid descriptions, and the required language param is not addressed in the description at all. Baseline 3 applies.

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?

Specific verb+resource: 'Retry narration generation for a video segment', with the triggering condition named. It is clearly distinguished from the sibling operations that create the segment in the first place (create_project_from_recording, insert_recording).

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?

Explicit precondition ('when create_project_from_recording or insert_recording returned scriptGenerated false'), explicit source of the arguments ('use exactly the projectUid and projectSectionUid returned by that operation'), and an explicit exclusion ('Call only when the user explicitly asks to retry'). All three when/when-not/which-input axes are covered.

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