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

Beyond annotations (destructive=true, idempotent=true), the description discloses atomicity ('the change is not partly saved'), retry guidance ('Preserve operation_id and exact inputs on retries'), cost ('Free: no credits'), and the account's direct-edit allowance. It adds rich behavioral context that annotations alone do not provide.

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?

The description is front-loaded with purpose and packs necessary details about alternatives, prerequisites, failure modes, retries, and cost. It is slightly verbose (six sentences) and could be more structured, but every sentence contributes useful information.

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?

Given the tool's complexity (mutation, nested parameters, idempotency, dependencies, cost) and the presence of an output schema, the description is complete. It covers prerequisites, failure behavior, retry semantics, and cost, leaving no critical gaps for correct invocation.

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?

With 80% schema description coverage, the baseline is 3. The description adds meaning by listing the caption fields (size, position, style) and noting that values must come from the project and that font changes are refused on certain styles. However, it doesn't specify where to find the supported values (e.g., browse_styles), leaving a small gap.

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 states a specific verb+resource ('Change caption size, position or style') and explicitly distinguishes from fix_captions for text changes. An agent can immediately tell what the tool does and when it differs from siblings.

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 names the alternative tool for spelling/text ('For spelling or caption text use fix_captions'), gives a prerequisite ('Read get_project_context first and pass its base_version and selected output_id'), and explains how to request a file separately via check_video. This covers when and how to use the tool explicitly.

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