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

Annotations only mark readOnly=false, destructive=false, and idempotent=false; the description adds meaningful behavior beyond that: saving creates a new version, the auth flow is never recorded and may use credentials, and the main kind becomes the video. This gives the agent useful context about side effects and credential handling.

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 succinct sentences, each earning its place: purpose, kind semantics, and prerequisite. There is no filler or repetition.

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?

The description covers purpose, the auth/main distinction, and the validate_guide prerequisite; the input schema covers all parameter semantics at 100%, and an output schema exists, so return values need no description. It might have named project_id's source, but that is already in the schema.

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 baseline is 3. The description reinforces the kind distinction already in the schema but introduces no new meaning for name, content, project_id, or video_title beyond their schema descriptions; therefore it stays at 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?

Description opens with a specific verb and resource: 'Save a guide on a project as a new version,' which clearly identifies the mutation and distinguishes it from read/list siblings like list_runs. It further clarifies the two kinds, so an agent can tell it apart from validate_guide without opening the schema.

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 explicitly instructs 'Run validate_guide first,' which establishes the workflow context and the validation prerequisite. It does not enumerate alternative tools or state when not to use, but no sibling performs a guide save, so the 'Save a guide' statement plus validator prerequisite is clear context.

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