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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds genuinely useful behavior: it can return multiple plausible matches and must be disambiguated before any write. It also warns which value formats are invalid to pass. It does not describe ranking or result ordering.

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-loads the core purpose and the trigger example before the ID mechanics. The trailing ID-sourcing block ('Obtain with: ... Never pass: ...') is dense and somewhat tangential to resolving, but each sentence carries usable instruction rather than filler.

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?

With no output schema and a nested 'filters' object, the description should say more about what comes back (a ranked candidate list? how many?) and how 'limit' defaults. It hints at multiple results via the disambiguation rule but never specifies the return shape, leaving a real gap for a 6-param tool.

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%, so the description must compensate. It usefully explains what 'keywords' should contain and clarifies the ID format, but it says nothing about 'limit', 'save_search', or 'save_custom_filter' (which are schema-only, not-null constraints), leaving real ambiguity at low coverage.

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: resolves a free-text human description (name, role, employer, location) into LinkedIn people and stable system IDs, and clarifies it runs 'before an action'. It does not explicitly differentiate itself from closely-named siblings such as linkedin_search_people or linkedin_resolve_company, so an agent must infer the split.

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 a concrete trigger ('Use when the user says message Sarah at Acme or connect with the CTO of X rather than providing an ID') and a disambiguation rule ('If multiple plausible results remain, show/disambiguate them before any write'). It does not name the sibling searches it should replace, so alternative selection is left partly implicit.

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