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

With annotations already signaling a non-destructive, closed-world write, the description adds genuinely new behavior: the default that it 'lands in the board's first status' and the two-phase approval flow ('May return `needs_confirmation` — summarize and wait for approval'). These are non-obvious traits an agent must handle, not restatements of annotations.

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 core action, then each sentence covers one decision (anchoring, default status, experiment, approval). No filler; every clause carries an actionable instruction.

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 9-param create tool with no output schema, the description covers anchoring, status defaulting, experiment gating, and the needs_confirmation exceptional return. It does not describe the success return shape (e.g., the created opportunity's id/link), which is the only meaningful gap.

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% with rich per-parameter descriptions, so the baseline would be 3, but the prose adds decision logic the schema lacks: when to anchor workflowPageId, when to set statusName, when experiment applies, and how approvalId follows a needs_confirmation response. It reinforces and contextualizes rather than introducing new syntax.

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+resource ('Record a change') and enumerates concrete examples (fix, chore, new step, experiment), so the agent knows what lands in the board. It does not, however, differentiate itself from close siblings like compass_opportunities_propose or compass_changes_upsert. Clear on what it does, silent on how it differs from neighbors.

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 explicit conditions for the key decisions: anchor to a workflow page 'when one fits' (with compass_pages_list), leave unanchored otherwise, and set `experiment` 'only when the user wants it measured against the Ledger.' It also names compass_statuses_list for status selection. No exclusion against the sibling `propose` tool, so it stops short of full routing.

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