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

With no annotations, the description carries the full burden and does so well: it discloses that values are validated and clamped to the chosen model's capabilities, that an unknown model is rejected, that the change persists as the base for future generations, and that the response includes updated settings plus cost. It does not say what happens with an empty call or whether any auth scope is required, which are the remaining gaps.

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 but front-loaded: the confirmation precondition and partial-update rule lead, and each subsequent sentence adds distinct information (validation, persistence, aspect-ratio map, rename scoping, return value). The mid-paragraph aspect-ratio aside slightly interrupts the flow between the settings and rename aspects.

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 14-parameter mutation tool with no annotations and no output schema, the description is unusually complete on behavior, guardrails and return values. The residual gap is parameter-level documentation for the model/quality/duration fields, which neither the schema nor the description supplies.

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 14% across 14 parameters, so the description must compensate, and it only partly does: it explains the aspect-ratio vocabulary (9:16 social/portrait, 16:9 YouTube, 1:1 square) and the rename semantics of project_name. The model names, speech_speed, video_duration, video_resolution, image_quality and video_sound still have no value guidance anywhere, so twelve parameters remain semantically thin.

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?

Names a specific verb (change settings) plus a second explicit action (rename the project via project_name), which lets an agent separate it from read-side siblings like get_settings. It does not explicitly name get_settings as the read counterpart, so the differentiation is inferred rather than stated.

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 explicit when-to-use rules ('AFTER the user confirms — never pick a model or format for them unprompted'), an exclusion for renaming another project ('tell the user to ask in that project's chat'), and an alternative path (project_name on generate/ingest_url). It also states the partial-update rule ('pass only the keys to change'), leaving little to inference.

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