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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false), but the description adds real value beyond them: it discloses the search corpus (people and pages recently tagged on this workspace plus followers of its LinkedIn pages), which explains why a plausible name can miss. It also discloses the return shape `{name, urn}` and that multiple matches come back with headlines, despite there being no output schema. It does not say what happens when neither `url` nor `name` is supplied, which matters given zero required parameters.

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 is a single dense paragraph, but it is front-loaded with the action and the follow-on call, then the parameter choice, then the disambiguation rule, then the scope limit — a sensible priority order. A few clauses are packed with parentheses and embedded examples, so it reads slightly run-on, but no sentence is 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?

For a read-only lookup with no output schema, it covers the full loop: how to search, what comes back, how to use the `{name, urn}` result downstream, how to handle ambiguity, and where tags do not apply. The one omission is the zero-required-parameter behavior when both `url` and `name` are 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 meaning the schema does not: `url` is characterized as resolving to exactly one person or page, and `name` is characterized as searching a specific bounded corpus rather than all of LinkedIn. That distinction changes how an agent should interpret empty results, which is genuine added semantics. It says nothing extra about `workspace` or `connected_account_id`, but their schema text already covers the defaults and the select_workspace contrast.

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 opening clause states a specific verb and resource: "Find who to tag in a LinkedIn post," with concrete example phrasings ("tag Jane Doe", "@ Sam in the post"). It also names what it is not for by tying its output to save_draft/update_draft `linkedin_tags`, so an agent can distinguish it from the drafting siblings 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?

Explicit ordering guidance ("look them up here FIRST"), explicit choice between the two lookup modes (url when the user has it, name otherwise), explicit disambiguation policy ("ask the user which one they mean, never pick one yourself"), and an explicit no-match fallback ("ask the user for the profile URL"). It also states a hard scope exclusion: tags work in the post body only, not first comments, not other platforms.

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