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

Annotations only declare it is not read-only, not destructive, and not open-world; the description adds the costly part (spends AI credits), the scope limit (latest run only), and the full two-phase confirmation contract with status='confirmation_required', action_id, and plan_token. That is substantial value beyond the annotation flags, though it does not discuss failure modes if the token expires or the run changes.

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 what the tool does, then the credit cost, then the scope, then the confirmation mechanics in a labeled clause. Every sentence contributes a distinct fact with no filler.

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?

Although there is no output schema, the description defines the expected return (status='confirmation_required' with action_id and plan_token) and the follow-up tool needed to finish. For a one-parameter, non-destructive mutation gated by confirmation, nothing operational is missing.

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?

There is a single parameter with 100% schema description coverage pointing to seo_list_projects for the id, so the schema already carries the semantics. The description adds no further detail about project_id, which is acceptable at this coverage but not above 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?

States a specific verb ('continue') and resource ('a finished research') and clarifies exactly what gets added — the stages that did not exist when it ran, e.g. page proposals. The scope restriction 'applies to the project's latest run only' further separates it from seo_start_research.

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 routes the agent: check seo_project_status first for the continuation and its estimate, tell the person the price, then call this tool, and use confirm_action to complete the write. Both prerequisites and the alternative path are named.

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