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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses genuinely non-obvious behavior: staffing agencies and job boards are excluded from results, ambiguous company names are reported in warnings rather than silently resolved, and compact reads are cheaper with a free daily allowance for connected assistants. This is exactly the kind of cost and edge-case context the annotations cannot carry.

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?

It's a single dense paragraph, but the defining clause ('lookalikes of one company: companies that share...') is front-loaded before the use cases, exclusions and cost notes. Nearly every clause carries information an agent needs; the trade-off is that the run-on structure makes it harder to scan than a short bulleted form.

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 filtered similarity-search tool with an output schema already defining the return shape, the description covers the remaining gaps: what similarity means, what is intentionally excluded, how ambiguous input is handled, and the cost model. Nothing an agent needs in order to call it correctly is absent.

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, but the description adds real meaning: 'company' accepts an Alion id, domain or name and ambiguity surfaces in warnings, and 'country' acts as a hard narrowing filter on office location. The detail=compact field list largely duplicates the schema description, which caps this below 5.

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 verb and resource ('lookalikes of one company') and then defines similarity concretely: shared industry segments, technologies named in job postings, headquarters country and a near size band. It also distinguishes itself from the sibling search_companies by describing rows as 'a company (as in search_companies) plus similarity', so an agent can tell the two apart without opening either 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 gives concrete use contexts — market map, competitor scan, prospect list from a best customer, alternatives to a supplier — plus a narrowing rule ('Narrow to one country with country'). What's missing is explicit negative guidance: it never says when to prefer get_company, resolve_company or search_companies instead, so routing is implied rather than stated.

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