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

Goes well beyond the annotations by explaining the consequence model: nothing was ever sent, there is nothing to undo, and the action cannot be reversed once called. It also discloses that reason is not stored or displayed anywhere and that the equivalent Settings > MCP > Xero path remains available, so the agent won't overstate what the call accomplishes.

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?

Dense but front-loaded: the action and its irreversibility come first, then the consent gate, then parameter guidance, then the UI alternative. A few clauses (the reason-disclosure sentence, the Settings > MCP > Xero note) are repeated in substance from the schema, which trims the score slightly.

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 pending-change tool with no output schema and full schema coverage, it supplies everything an agent needs: prerequisites, consent bar, irreversibility, post-call honesty about reason, and a fallback path. Nothing material is left to inference.

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; the description adds procedural meaning by tying confirm to a consent gate and sequencing it after informing the user ("Make sure they know what they are turning down first ... then call this with confirm: true"). The reason guidance largely restates the schema's own description, so it is reinforcement rather than new semantics.

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 ("Rejects a change ... proposed to Xero") and immediately scopes the effect: the change is discarded and never reaches Xero. It implicitly but unmistakably distinguishes itself from the sibling approve_xero_pending_change and from the list tools that surface these rows.

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 when-to-use conditions (only after the account holder has clearly said, in their own words, to discard THIS change) and explicit when-not conditions (never from silence, a change of topic, or them not mentioning it). It also names the prerequisite alternative: call list_pending_changes first if the summary is not already in conversation.

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