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

Annotations supply destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds genuinely non-obvious behavior: partial-update semantics, the needs_confirmation/approvalId loop, and that an assignee triggers a notification. It does not explicitly warn that tags/notes replace rather than merge, which the destructive annotation implies but the prose only hints at.

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 core action and the mutable-field list, followed by the constraint/alternative and the confirmation flow. No filler; every clause carries operational information.

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 an 18-parameter mutation with no output schema, the description covers id provenance, the confirmation protocol, and sibling routing, which is most of what an agent needs. It stops short of documenting return values or the exact consequences of null-clearing fields, but the essentials are present.

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 83%, so most parameters are already self-documented. The description restates a handful of fields (owner is a PERSON page, 1–5 scores) that the schema largely covers, adding little syntax or format detail beyond it. Baseline 3 is appropriate when the schema carries the load.

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?

Starts with a specific verb+resource ('Corrects an opportunity's content') and enumerates exactly which fields are editable, then explicitly carves out what is NOT editable ('the lane is NOT here — move it with compass_opportunities_set_status'). An agent can distinguish this from sibling updaters without opening the schema.

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 the partial-update contract ('Fields you omit are untouched'), routes the lane change to the correct sibling, tells where opportunity ids come from, and explains the needs_confirmation handshake including the instruction to pause and confirm. Multiple when/when-not conditions, nothing left implicit.

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