Update change order

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

Annotations already declare non-read-only, non-destructive, non-idempotent, open-world, so the description doesn't owe a safety profile. It still adds real behavior: merge semantics, that a status of the wrong kind aborts the call (a validation error, not a silent mis-set), and that no notification email is fired. Gaps remain on permission requirements and whether status transitions can be reverted.

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 and the partial-update rule, then the status taxonomy, then the side-effect caveat. Every sentence carries information; the two status enumerations are slightly redundant against the schema enum but earn their place by explaining the split.

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 5-param mutation with no output schema, the description covers merge semantics, enum ambiguity, failure mode, and notification side effects — enough to call it correctly. Missing only permission/prerequisite context and any note on reversing a billed/approved status.

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 only 20% (only change_order_id is documented), so the description must compensate, and it largely does: it enumerates the two families of status values and explains why the single status enum contains both 'open/approved/pending_approval' and 'draft/closed'. The 'reason' vs 'description' naming mismatch is the one place the description misleads rather than clarifies.

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 plus the fields it mutates, so it's clearly distinct from create_change_order, delete_change_order, and send_change_order. Minor flaw: it names 'reason' as an updatable field, but the schema exposes 'description' and no 'reason' property, so an agent could look for a nonexistent field.

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 explains the partial-update contract ('Sets only the fields you pass') and routes the notification case to send_change_order ('Nobody is emailed. send_change_order does that'). It doesn't state hard exclusions (e.g., which status transitions are disallowed beyond the kind mismatch), but the intended context is clear.

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