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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the "Read-only" line mostly restates structured data. The description does add genuinely new behavioral context: the plan restriction ("Paid plans only") and a detailed inventory of what is returned, but it omits failure behavior for missing or inaccessible recommendations.

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-loaded with the verb and the payload, then two short operational sentences. The long parenthetical enumeration of evidence fields is dense but every item informs what the agent will receive, so little is wasted.

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 no output schema, the description carries the return-value burden itself and does so thoroughly, listing steps, evidence, published page, and workspace contents including draft Markdown. Combined with the paid-plan note and the anti-fabrication instruction, an agent has what it needs to call and use the result 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 coverage is 100%: both parameters are documented in the schema, including that project accepts an id or address from list_projects and that recommendation_id comes from get_recommendations. The description adds no further parameter meaning, so the baseline 3 applies.

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 ("Get one recommendation") and enumerates the payload: steps, evidence with cited pages, the published page, and the workspace. The singular "one" plus the schema's pointer to get_recommendations makes the distinction from the sibling list tool inferable, though the description itself never names get_recommendations as the place IDs come from.

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 a clear usage context: "Use it before writing the e-mail or page with the user" plus a guardrail ("never invent facts, reviews or testimonials"). It stops short of explicit exclusions or naming alternatives such as get_recommendations for listing or update_recommendation for mutations.

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