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

Annotations already cover readOnly/destructive/openWorld, and the description adds real value beyond them: validation is independent per row, invalid rows are flagged, a short-lived receipt is returned, and the allowlist constraint on commit.tool is stated. It does not address rate limits or the exact error surface, so it falls short of a 5.

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 a labeled "When to use" and "Example", but the middle paragraph is dense and packs workflow edge cases together; "It commits NOTHING itself" is effectively repeated in the when-to-use section, which is mild redundancy rather than waste.

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?

Given the tool's workflow complexity and an existing output schema (which covers the return/receipt), the description covers the tricky sequencing (create-before-link, lead retirement, batch splitting) and validation behavior thoroughly. Minor gaps remain around error handling, but nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so baseline is 3, but the description goes further by explaining commit.args semantics that the schema leaves as open objects: create_record/update_record generic verb arg shapes ({object_type, data}/{object_type, id, patch}), the resolved-UUID requirement for id, and carrying source_touch_id from propose_updates.

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 ("Present atomic proposed CRM updates for field-by-field approval") and immediately distinguishes itself from siblings, notably commit_reviewed_updates via "It commits NOTHING itself" and propose_updates via the when-to-use context. An agent can route to this tool 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?

Explicit "When to use: Right after propose_updates, or whenever you've assembled atomic updates from a prompt" plus a detailed ordering protocol (creates first, then link-rows in a second review, retirement in a third, split large batches). The alternative commit_reviewed_updates is named with the condition (after explicit selection, with the unchanged receipt).

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