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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial domain behavior: a check is 'done once and covering every model that shares it', a 'waiting' state means a check started in the last 30 minutes, and 'not_needed' also covers AI-made characters. That 30-minute staleness window and the cross-model sharing semantics are things the agent could not derive from the schema or annotations.

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?

It is information-dense with little outright filler, but the structure is poor: the opening clause is convoluted and grammatically broken, and the status enumeration is packed into one long colon-chained sentence. A reader must re-parse the first line to figure out what is being returned, so it is not well front-loaded despite being short.

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?

With only two fully-documented parameters, no output schema, and annotations covering safety, the description supplies the missing piece: the enumerated status values and what each means, including the failure remediation. What remains unstated is the exact response shape beyond the status value, which is minor for a simple lookup.

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% and both parameters are documented with an enum for model, so the schema does the heavy lifting. The description adds only modest meaning, linking the model parameter to the get_options music_video.models[].face_check flag and clarifying that character_id represents a real person (performer or people in the video). That is useful but thin relative to the schema baseline.

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?

The description conveys the domain meaning well ('whether a model can show this real person yet', face check status), but the leading clause is grammatically broken ('their face check for it') and never uses a clean verb like 'returns the face check status'. It does not explicitly distinguish itself from the sibling read/write pair start_face_check and withdraw_face_check, so the agent must infer that this is the read variant.

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?

It gives concrete timing guidance: 'Asked before quoting such a model for each real person in it (the performer and the people)', which tells the agent exactly when in the workflow to call it and that it must be called per real person. The failure state even points toward remediation ('start another'), though it does not name start_face_check explicitly as the alternative tool.

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