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

Annotations already flag mutation (readOnlyHint=false), idempotence, and non-destructive intent. The description adds meaningful side effects: 'creates or updates a durable Salesbot company list', returns prospect_company_id, and optionally creates CRM records. It does not contradict annotations; it enriches them.

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 front-loaded with the core behavior in sentence one, scoping/exclusions in sentence two, and a compact actionable workflow in sentence three. No filler; modest length is justified by cross-tool workflow guidance.

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 mutating importer with no output schema, it covers return values (prospect_company_id), side effects (durable list, optional CRM write), and next steps. Cursor/limit behavior is already documented in the schema, so nothing critical is missing. Slight gap is lack of detail on failure/partial-import behavior but not essential.

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 covers 100% of parameters with descriptions (e.g., limit default, cursor, list_name, search_url, save_to_crm), so baseline is 3. The description repeats URL source and durable-list semantics but does not add parameter-level detail beyond the schema.

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 action ('Import and persist companies'), the source ('LinkedIn company search URL or Sales Navigator account-search/list URL'), and the output ('returns prospect_company_id'). It explicitly disambiguates from people-focused tools with 'not people' and connects to sibling workflow. This is a clear verb+resource definition.

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 triggers (company search or Sales Navigator account/list URL), an explicit exclusion ('not people'), and a step-by-step follow-on workflow naming list_companies, search_web/scrape_website, update_company_research, search_linkedin_people, and upsert_linkedin_contact. It does not explicitly contrast with add_companies_to_crm, but the 'not people' and durable-list framing provide enough routing context.

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