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

Annotations already mark readOnlyHint, and the description adds substantive behavior: follow the playbook exactly, positioning_pass is read-only and fully autonomous, flow_pass reports broken/confusing steps and emails sent, and all playbooks yield a shareable Cobalt review. No contradiction with 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?

Every sentence carries operational value: fetch instruction, trigger conditions, available playbook behaviors, shared outcome, and the URL-fetch pitfall. The primary action is front-loaded, and there is no fluff.

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 2-parameter read-only fetch tool with no output schema, the description explains trigger conditions, playbook semantics, execution expectations, and the outcome. It even warns against a common wrong approach (URL fetching), leaving little ambiguity.

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 100%, so the baseline is 3; the description lifts it by enumerating valid name values and what each playbook does (usability_pass, positioning_pass, flow_pass). It adds little beyond the schema for url, but the playbook semantics are the crucial parameter meaning.

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 action ('Fetch a Cobalt test playbook by name'), names the resource, and instructs the agent to follow it exactly. The three named playbooks make its scope concrete, and it is clearly distinct from the review/inbox sibling tools.

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?

Explicitly says when to invoke: for usability pass, QA run, first-time-user review, or positioning/messaging audit when the playbook text is not already held. It also gives a when-not/preference rule: prefer this over URL fetching because web fetchers summarize and silently drop instructions.

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