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

Annotations only declare readOnly/openWorld/non-destructive; the description goes well beyond them by disclosing that titles and descriptions are sent to an external AI provider, that features.manage is required as an elevated scope, that scans are capped at 500 other active requests and error out on larger/incomplete sets, and that at most 20 candidates are analyzed. It also flags member-authored text as untrusted prompt-injection risk — exactly the kind of behavior an agent cannot infer from 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?

Every sentence carries distinct, decision-relevant information — scope, permission, data egress, exclusions, scan limits, return semantics, and prompt-injection caution — with no filler or repetition. The scoping sentence is front-loaded and the caveats follow in priority order.

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?

Despite no output schema, the description explains what results contain (advisory scores and explanations), their limitations (never edits or merges), and the failure mode (error on oversized/incomplete scans). Combined with auth and data-handling disclosures, an agent has everything needed to invoke and safely interpret this tool.

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 33% (only feature_id is documented, with a pointer to list_features/search_features). The description never mentions the limit or similarity_threshold parameters, so it does not compensate for the undocumented parameters; the implicit 'at most 20 candidates' is a hint at limit but adds no usable semantics.

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 — finding likely duplicates of an active request, scoped to 'its own board' — and ties it to the same AI analysis used in the admin UI. This clearly separates it from siblings like search_features or list_features, which retrieve rather than analyze for duplication.

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 clear preconditions (target must be an active request on its own board) and explicit exclusions (Archived, Done and Not Planned are not scanned), plus the features.manage requirement even on read-only connections. It never names a sibling alternative for cases where duplicate detection isn't wanted, so it stops short of a 5.

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