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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds a critical behavioral nuance: LinkedIn mentions require the numeric company ID, not the slug, and clarifies that the result is a set of company IDs. It doesn't describe return format or error behavior, but given the annotation coverage, it adds useful context beyond what is already structured.

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 description is somewhat verbose and contains redundant statements: 'LinkedIn company mentions require the numeric company ID; the slug from /company/google/ is not sufficient.' and later 'For mentions LinkedIn requires numeric company ID, not the company URL slug.' convey the same point. The 'LinkedIn company ID: Provider numeric/company ID.' sentence adds little. While the key directives are front-loaded, the redundancy could be trimmed without losing meaning.

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?

There is no output schema, so the description should clarify the return structure. It mentions 'LinkedIn company results and exact company IDs' but doesn't specify whether it returns a list, a single match, or how to select among multiple results. The workflow references other tools, which helps, but the 'filters' parameter is completely unexplained. Given 3 parameters and a nested object, the description leaves notable gaps for an agent to call the tool correctly.

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 only 33% (only account_id has a description). The description clarifies that 'keywords' should be a human company name (from the opening sentence) and indirectly warns against passing URLs or slugs. However, it provides no explanation for the 'filters' parameter, which is a nested object and could be ambiguous. The description adds some semantic value for keywords but falls short of compensating for the undocumented filters.

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 clearly states what the tool does: 'Resolve a human company name to LinkedIn company results and exact company IDs.' It specifies the verb (resolve), the input (human company name), and the output (results and numeric company IDs). It also distinguishes itself from siblings by indicating it should be used before employee searches, company profile reads, or company mentions, and explains that the numeric ID is required for mentions, differentiating it from URL-slug-based tools.

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?

The description gives explicit when-to-use guidance: 'Use before employee searches, company profile reads or company mentions.' It also provides a workflow: 'Obtain with: linkedin_search_companies -> selected result.id; linkedin_get_company after resolving a company' and clear exclusions: 'Never pass: linkedin.com/company/google URL, company slug such as google, company name.' This tells the agent exactly when to invoke the tool and what inputs to avoid.

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