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

Annotations declare destructiveHint=true, and the description adds crucial nuance beyond them: this is a soft delete, and the call may return `needs_confirmation` requiring an approvalId on a follow-up call. That disclosure of the confirmation flow and the soft-delete semantics is exactly the behavioral context annotations cannot convey.

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 action and its soft-delete nature, followed by the routing guidance and the confirmation caveat. Every sentence earns its place; no filler.

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?

For a destructive-flagged mutation with no output schema, the description covers the operation semantics, when to prefer an alternative, id provenance, and the needs_confirmation return path. 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 coverage is 100%, so the schema already documents all three parameters, making 3 the baseline. The description earns a bump by tying the `needs_confirmation` return to the approvalId parameter and stating that ids come from compass_opportunities_list, adding source-of-value context the schema lacks.

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 ('Removes an opportunity from the pipeline') and immediately qualifies the operation as a soft delete. It further disambiguates from sibling operations by naming the two distinct intents — dismiss for AI proposals, remove for duplicates/mistakes — so an agent can tell it apart from compass_opportunities_accept or set_status.

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 routes the agent: names the alternative tool (compass_opportunities_set_status REJECTED) and the condition that selects it ('to conclude a real experiment without evidence ... that keeps the record'). It also states where ids originate, leaving nothing to inference.

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