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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false): it states nothing is saved or posted, names the required permission and which roles hold it, documents the 403 permission_denied code, quantifies the cost as 2 AI credits with refund-on-failure semantics, and prescribes behavior when credits run out (explain unavailability, do not auto-retry). This is unusually rich behavioral disclosure for a generation tool.

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?

Front-loads the core purpose in the first clause, then layers operational details in a single dense paragraph with no filler. Some sentences pack permission, credit, and failure semantics together, which is heavy but each clause 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?

With an output schema present, return values need not be explained, yet the description still states it returns { caption }. Between the description and annotations, an agent has purpose, permission model, cost, failure handling, and non-persistence — everything needed to invoke correctly.

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 the schema already documents all five parameters, including platform's enum and the partialText/originalText distinction. The description reinforces the purpose of platform and partialText but adds little syntax or interaction detail beyond the schema (e.g., it does not say how partialText and the required originalText combine). Baseline 3 is appropriate.

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 ("Rewrite an existing caption following an instruction") and immediately distinguishes itself from the sibling generate_caption by operating on an existing caption rather than producing a new one. The example instructions ("shorter", "more playful") make the operation concrete.

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 clear contextual triggers: send partialText to continue a partly written caption, pass platform to target a character limit, check the returned text before posting, and compares cost to generate_caption. It never states the inverse routing rule (use generate_caption when there is no existing caption to rewrite), so the alternative is implied rather than explicit.

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