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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with that ('without saving', 'no policy activation or publication'). Beyond the annotations it adds genuinely useful merge semantics (omitted fields preserved, empty strings clear optional fields) and stale-revision behavior. However, it does not describe the shape of the returned normalized values or what a validation failure looks like, so it stops short of full behavioral disclosure.

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?

The precondition and upstream call are front-loaded, and every sentence carries distinct information with no filler. The staccato phrasing ('Stale revision requires reread and renewed intent', 'No policy activation or publication') is efficient but borders on telegraphic, which slightly raises parsing effort.

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 nested, two-parameter preview tool with no output schema, the definition covers the prerequisite read, the revision contract, the patch merge rules, the human-approval handoff, and the absence of side effects. An agent has everything needed to invoke it correctly and to interpret the outcome.

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?

With schema description coverage at 0%, the description carries the burden and does so for the critical parts: expectedRevision must be copied exactly from get_company_profile, and patch is a partial update where omitted fields are preserved and empty strings clear optional values. What it does not cover is per-field meaning and format for the ten nested patch properties (country_code, website_url, phone_number, representative_role), which remain undocumented in both schema and description.

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?

The description names a specific operation on a specific resource: validating a company-profile change request and returning normalized final values without saving. It is immediately distinguishable from get_company_profile (the read it depends on) and from show_company_profile_approval (the human-execution path), so an agent can select it 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?

It states the precondition explicitly ('After an explicit company-profile change request'), names the required upstream call, and routes the alternative case to show_company_profile_approval 'with identical input'. It also gives the failure path: a stale revision requires a reread and renewed intent rather than a retry.

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