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

With readOnlyHint=true and destructiveHint=false already declared, the safety profile is covered by annotations. The description adds useful behavioral context — default sort (newest first), pagination, and filterability by status — which goes beyond what annotations say. It stops short of explaining pagination mechanics (offset/limit usage) or total-count semantics.

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. The purpose and routing information are front-loaded; pagination and filtering are appended without redundancy. Every sentence earns its place.

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 list tool with no output schema, the description gives enough to call it correctly (what it returns conceptually, sort order, pagination existence, filterable field). What's missing is the shape of the return (array of project objects with projectId and status) and pagination parameter semantics, but annotations cover safety and the routing use case is clear.

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 only 33%, so limit and offset have no schema description. The description compensates partially by mentioning pagination and status filtering (with an example 'completed'), but does not explain limit/offset semantics or defaults. The status parameter's enum is self-documenting in the schema, so the description's status mention is mild added value.

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 (list) and resource (video projects), adds ordering ('newest first'), and names the exact downstream consumer tools (upscale_video / voice_enhance / dub_video). This differentiates it from siblings like get_video (single fetch) and create_video.

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 states when to use it: to find a completed project's projectId for post-processing, or to check generation status. It also names the alternative pattern (get_video for single retrieval) implicitly by citing the post-processing tools. No ambiguity remains for an agent choosing among the video tools.

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