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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds genuinely new, non-structured information: 10 credits per page and the advice to narrow filters before paginating. It does not describe result volume, page caps, or what an empty result means, so it is not fully transparent.

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 purpose, then filter semantics, then cost, then workflow. Every sentence carries weight. Slight redundancy between the purpose line and the closing workflow sentence, but nothing is wasted.

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?

An output schema exists, so return values need not be explained, and annotations carry the read-only/idempotent profile. The remaining gap is filter-value discovery for 7 undescribed parameters — the description should have named suggest_filter_values or list_filter_values as the way to obtain valid strings.

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 0% across 7 parameters, so the description has to compensate. It does add important semantics — filters accept human-readable strings or lists of strings that are OR-ed together — which resolves the array-combination ambiguity the schema cannot. But per-parameter formats (followers_count as a string, headcount ranges, valid industry values) are undocumented, and it fails to point to list_filter_values or suggest_filter_values for discovering valid values.

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: finds accounts/companies matching an ICP. It also distinguishes itself from search_people as the account-level counterpart to the people-level search, so an agent can route between them. It never says 'company database' explicitly, but 'target accounts' is unambiguous alongside the tool name.

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 sequencing: build the account list here, then call search_people with company_name or company_linkedin_urls to find people at those accounts. That is explicit alternative-routing. No when-not conditions are stated (e.g., don't use this for a single known company — use get_company_profile), which keeps it below a 5.

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