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

Annotations already declare readOnly/openWorld/non-destructive, yet the description still adds substantive behavior: it returns up to 5 candidate URNs for human disambiguation, it refuses personal URLs under a stated precondition, and it warns that LinkedIn's API silently drops arbitrary person URNs. These are non-obvious constraints an agent could not infer from structured fields.

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?

Purpose and accepted input forms are front-loaded, followed by output cardinality, then the downstream hand-off and the failure precondition. Every sentence carries distinct information; nothing is repeated from the title or schema.

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 two-parameter read-only resolver with no output schema, the description covers what it returns (up to 5 candidate URNs), what to do with the result, and the key failure mode. The workspace-connection precondition is also reinforced in the schema, so nothing needed to call it correctly is missing.

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 goes further by enumerating the concrete query input shapes — bare vanity ('shortsync'), full URL, display name ('ShortSync'), or pasted org URN — with worked examples that make the format ambiguity actionable rather than abstract.

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 (resolves) and a precise resource (LinkedIn Company Page or workspace-member person) and names the exact output artifact (`urn:li:*` identifier for Posts API mentions). This is distinguishable from every sibling, most of which deal with posts, folders, or analytics rather than identifier resolution.

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?

Clearly frames the workflow context: call it to get a URN, then 'Feed the picked `urn` into upsert_workspace_person as platform_urns.linkedin' so the mention publishes with a real card. It also states a when-not condition — personal LinkedIn URLs are refused unless the person has connected LinkedIn to the workspace — and explains why (the API silently drops arbitrary person URNs). No sibling alternative exists to contrast against, which keeps it just short of a 5.

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