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

Annotations only flag destructive/non-idempotent; the description goes far beyond with partial-update semantics (unspecified fields stay put), standing/board position being unaffected, null-clearing behavior for why and pagesToFix, equal-value edits producing no activity, and bounded return plus retry guidance. Rich context an agent cannot get from the structured fields.

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?

Dense but front-loaded: what it edits and what is excluded come first, then field semantics, then return/retry behavior. Every clause carries information, though the long single paragraph is dense enough to slow scanning slightly.

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 an output schema present the description needn't explain return values, and annotations cover the safety profile; the description still covers mutation semantics, clearing edge cases, and retry-after-uncertainty. Nothing an agent needs to invoke it correctly 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?

Schema description coverage is only 8% across 13 params, so the description must compensate, and it does meaningfully: evidence sourcing/clearing, why:null, pagesToFix:null/[], and the non-nullable constraints on title/question/whatToDo and grades. It stops short of explaining the intent enum or targetStanding's meaning, so it is strong but not exhaustive.

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 (edits) plus the exact resource and scope: user-created recommendations in this Account, including ones made by other authorized users. An agent can immediately distinguish it from create_recommendation, archive_recommendation, and the read tools 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?

Gives explicit exclusions ('scan-raised recommendations cannot be edited, and one that has been confirmed or archived cannot either') and routes the agent to related tools: get_narrative_claims for claimIds and get_recommendation before retrying after uncertain delivery. This is a clear when/when-not with named alternatives.

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