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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description reinforces 'Read-only' and adds the genuinely useful lifecycle context that proposals and signals are acted on elsewhere (confirm_staged_changes / stage_*), which the annotations cannot convey. It does not mention pagination or rate behavior, keeping it short of a 5.

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?

Two dense sentences, front-loaded with the identity of the resource before the parameter guidance. Every clause carries information (row shape, id format, downstream tools), though the long parenthetical enumeration of signal types is slightly list-heavy.

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?

There is no output schema, and the description compensates by describing the returned row shape (department, severity levels act_now/review/info, count, impact estimate) and the two modes of use (queue vs evidence packet). Combined with readOnly annotations, an agent has everything needed to call 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 100%, so the baseline is 3, but the description goes beyond the schema by giving concrete item id syntax (signal:budget_caps, proposal:123), explaining that item returns the evidence rows behind a queue entry, and restating the department tab semantics. It adds real meaning over the field descriptions rather than merely echoing them.

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 resource (the Decisions queue) with its exact semantics: owner-desk ranking, and enumerates what it contains (staged proposals, optimizer batches, platform signals) plus the fields attached to each row (department, severity, count, impact estimate). It also names the sibling tools that handle follow-up actions, so an agent can distinguish this read-queue tool from confirm_staged_changes and stage_* without opening schemas.

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?

Explicitly tells the agent how to narrow scope: department= for one tab, item= for the evidence rows behind a queue entry, and omit department for the whole queue. It also routes downstream work to confirm_staged_changes for proposals and the matching stage_* tool for signals. It stops short of a full when/when-not comparison against other reporting siblings, so it is clear context rather than exhaustive routing.

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