List failed work

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

Goes well beyond the readOnlyHint annotation: it discloses the admin-only permission requirement, the hosted-tier refusal behavior, the aggregation semantics (child clips are collapsed into the parent project failure), and the truncation/nextCursor pagination behavior. These are exactly the traits an agent needs before calling.

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?

Dense and front-loaded: access restriction first, then scope, then the clip-aggregation caveat, then return shape, then filters. Slightly crammed, but nearly 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?

There is no output schema, yet the description names the return keys ({ items, nextCursor, total, limit, truncated }) and explains pagination via cursor. Combined with the auth and filtering notes, an agent has enough to call this correctly without inspecting anything further.

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%, so all five parameters are already documented with examples and formats. The description only restates q, stage, and since at a high level and says nothing about limit or cursor, so it adds marginal value over the schema — baseline 3.

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 ('failed projects and clips across the instance') plus the fields returned (owner email, stage, reason, when). It is clearly distinct from get_failure (single item) and retry_failures in intent, though it never names a sibling explicitly.

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?

Explicitly scopes the audience ('Admins only', 'Hosted non-admins are refused') and gives a concrete routing rule: a failed project's clips are not listed separately, so retry the project instead. It also tells the agent which filters to apply (q, stage, since), though it doesn't contrast against get_failure or retry_failures by name.

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