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

Goes well beyond the readOnly/openWorld annotations: declares the call is FREE (no credits), caps returns at 50 per call with an explicit 'same filters + nextCursor' paging rule, warns LinkedIn gives no total match count, notes postedBy requires a live LinkedIn sender of your own, and flags post/author text as untrusted third-party data that must never be obeyed.

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?

Dense but nearly every sentence carries load — filters, constraints, paging, next steps, safety. The front-loaded 'Ids in/Ids out' bracket block is compact output documentation standing in for a missing output schema, though it reads as jargon before the purpose sentence and slightly delays the front-load.

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, the description compensates by enumerating returned fields (text, date, link, reactions/comments/reposts, author name, headline, profile URL, providerId) and the id mapping, and it covers pagination, credit cost, auth prerequisite for postedBy, and the absence of location/total-count. Nothing needed to invoke or chain it 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 baseline is 3, but the description adds real disambiguation the schema cannot: authorCompanies = people who work at a company vs fromCompanies = the company page itself vs mentioningCompanies = @mentions (competitors), plus the operational note that postedBy needs a connected live sender. It does not restate defaults or enum values that the schema already carries.

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 ('Search LinkedIn posts by keyword and filters'), clarifies it is LinkedIn's native Posts search across all of LinkedIn, live, and gives three concrete use cases (finding people posting about a problem, competitor mentions, company page output). One gap: the sibling list contains a near-identically named 'search_linkedin_posts' that the description never distinguishes itself from, so an agent could still be unsure which search tool to pick.

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?

Explicitly recommends when to use it ('find people posting about a problem the user solves, posts that mention a competitor, what a company page is publishing') and when not to reach for a filter ('There is NO location filter for posts on LinkedIn — narrow by place in keywords or filter authors afterwards'). It also routes onward with concrete next steps (get_post_engagers, engagers_not_connected, get_recent_posts, save_lead bulk).

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