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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the "Read-only: returns public data and changes nothing" sentence largely restates structured data. The genuinely additive disclosures are the per-request cost ("Costs 1 credit per request") and the pagination continuation behavior, which the annotations do not convey. Return shape is partially covered by naming the included 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?

Three short sentences, front-loaded with the purpose, then pagination, then cost/safety — no filler. The only blemish is the `nextStart` token name, which is not in the schema and briefly creates a mismatch the reader must reconcile with `start`.

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 five-parameter read tool with no output schema, the description covers what is returned, how to page, that it is read-only, and what it costs — enough for correct invocation. Minor omissions remain: no statement about empty-result behavior or the interaction with cacheOnly/cacheMaxAgeHours, though the latter is fully covered in the schema.

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 description coverage is 100%, so all five parameters (count, start, publicId, cacheOnly, cacheMaxAgeHours) are already fully documented, including caching and cost behavior. The description adds no parameter-level meaning beyond that and its `nextStart` reference does not correspond to any schema property, so the baseline of 3 applies.

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 ("List every publication on a LinkedIn member's profile") and even enumerates the returned fields (publisher, publication date, description, link). The resource is inherently distinct from the many sibling profile-section tools (certifications, skills, honors), so an agent can select it without ambiguity.

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?

Provides one concrete procedural guideline — paginate using `nextStart` from the previous response — which tells the agent how to continue past the first page. However, it gives no when-to-use vs. when-not guidance relative to siblings such as linkedin_get_posts_from_profile, and the pagination token name (`nextStart`) does not match the schema's `start` parameter, leaving a gap the agent must resolve itself.

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