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

Goes well beyond the annotations: discloses that dry runs are non-writing, that a live push without approval returns a confirmation-required outcome, that the call is free, that it requires the pushes:write scope plus an app-made connection, and that records are matched/updated on mydatahub_record_id. The PECR audience caveat (corporate subscribers only by default, sole traders and ordinary partnerships excluded unless toggled) is exactly the kind of side effect annotations cannot express.

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 purpose, then defaults, then prerequisites, then compliance — a sensible order, and nearly every sentence carries operational weight. It is a dense single paragraph, and the UK GDPR Article 6(1)(f) / PECR tail is heavier than most agents need to select and call the tool, though it does inform the exclusion behavior.

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-parameter, open-world, mutating call with an output schema, the description covers everything an agent needs: safe default, approval mechanics, failure mode, required scope, connection prerequisite, and data-subject exclusions. Return values are correctly left to the output schema.

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 would be 3, but the description adds real meaning: dry_run's reporting semantics and the approval path that unlocks a live push, the mydatahub_record_id match key behind update_existing, and the person/scope/expiry/one-time binding of confirmation_token. It does not restate the ULID formats, which is fine since the schema already does.

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 ("Pushes an order's records to a connected CRM") plus the match key (mydatahub_record_id) and an explicit scope boundary ("as record operations only: nothing is ever sent to the contacts"). An agent can tell this apart from order-fetching or audience-building siblings without opening any 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 concrete operating guidance: dry_run defaults to true, "Show the dry run to the user before a live push," and a live push requires a person's confirmation or an agent key allowed push_to_crm. It lacks an explicit when-not-to-use clause or a named alternative (e.g., a quoting step), so it stops short of full routing guidance.

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