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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: permission-based visibility scoping by role (org.governance.review) and the not_found outcome for out-of-scope IDs, which the agent cannot infer from structured data.

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 scope, then a dense but purposeful enumeration of returned contents, followed by visibility and error behavior. Every clause carries information, though the long parenthetical and run-on comma list make it slightly heavy to parse.

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 burden of describing return values and does so thoroughly (reviews, quorum rows, current gate review round, criteria scores, linked project condition). Combined with the permission model and not_found behavior, an agent has everything needed to call and interpret it 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 0% and the description never documents the proposalId format or source. The only parameter-related value it adds is that out-of-scope proposalIds yield not_found, which hints at ID scoping but does not compensate for the missing format detail. With a single self-evident parameter, this remains minimum-viable.

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 governance proposal) and enumerates exactly what full detail comprises: business case fields, reviews, gate approvals with per-reviewer quorum rows, criteria scores, sponsor/submitter, and linked project. This enumeration implicitly distinguishes it from siblings like list_proposals, list_proposal_reviews, and list_gate_approvals by showing it aggregates them for a single proposal.

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 visibility clause ('reviewers see all; non-reviewers see only their own submissions') and the 'out-of-scope proposalIds return not_found' note give clear contextual guidance on what happens when called. It does not, however, explicitly name alternatives such as list_proposals or get_proposal_history or state a when-to-use condition, so it stops short of full routing guidance.

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