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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description meaningfully adds that only metadata is editable while storage identity is fixed, plus the approval gating flow through Settings > MCP and execute_approved_action. That is real context beyond the annotation flags. It stops short of saying whether omitted fields in the data object are preserved or cleared, which matters for a non-idempotent partial update.

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?

The approval-flow and storage-identity sentences are dense and load-bearing, but the first sentence is filler that front-loads noise ahead of the actual purpose, and its grammar ('documents records') is awkward. Roughly a quarter of the text does not earn its place.

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?

An output schema exists and annotations carry the safety profile, so the description need not cover return values. For a destructive, approval-gated mutation it covers the key operational facts: that nothing happens until approval and that storage identity is immutable. Remaining gap is field-level edit semantics for the nested data object and any per-organization permission specifics beyond the admin-configurable note.

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 0%, so the schema documents only types and UUID patterns for rfpId/documentId, and nothing about the nested data object's fields (name, fileSize, fileType, description). The description compensates only at a high level by calling the editable payload 'metadata' and the immutable part 'storage identity'; it never enumerates which fields are editable or explain the rfpId vs documentId relationship.

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?

The second clause states a specific verb and resource: 'Edit rfp document metadata', and 'cannot replace its storage identity' bounds the scope, which distinguishes it from attach_rfp_document and delete_rfp_document. The opening sentence ('Use this when working with RetailHardHat documents records in the connected organization') is boilerplate that adds no distinguishing information, and no sibling such as update_rfp is named.

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?

The description supplies a real precondition — no change occurs until a human approves the exact request and execute_approved_action is called — which tells the agent this is a two-step gated mutation. However, it never states when to choose this over update_rfp, update_site_document, or the other update_*_document siblings, so the caller must infer the boundary from the name alone.

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