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

Beyond the readOnly/openWorld annotations, the description discloses genuinely useful traits: results depend on Google's index, cursors are capped at page 11 with 400 beyond that, inline comments are only a public preview, and Pulse previews may return null dates and reaction counts. The cost statements undercut this ("at least 10 Nexscope credits" vs "1 credit per request"), leaving the actual billing behavior ambiguous.

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?

The first paragraph is dense but front-loaded with the right facts; the problem is the appended marketing/pricing block that repeats the purpose verbatim ("Search for public LinkedIn posts by keyword. Uses Google Search...") and adds boilerplate like "View Pricing" and "Examples are not guaranteed prices." Roughly a third of the text is redundant or contradictory 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, the description usefully enumerates returned fields (description, author, media, like count, comment count, published date) and the shape of inline comments including nullable timestamps. It is nearly complete for a three-parameter search tool, missing only result-count-per-page and ordering expectations.

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 query, cursor, and date_posted are already documented, including the cursor-11 limit. The description mainly restates those constraints and adds only that date_posted is based on Google-indexed results, so it hovers at the baseline for a fully documented schema.

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 first sentence names a specific verb and resource: finding public LinkedIn posts, feed updates, and Pulse articles by keyword via Google Search. That distinguishes it from single-item siblings like social_linkedin_post and scoped siblings like social_linkedin_company_posts, though no sibling is named explicitly.

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?

There is usable guidance on pagination (pass the returned cursor) and on the date_posted filter for recent posts, plus a clear limitation that results are best-effort and not a native LinkedIn search. However, it never says when to choose this over alternative tools (e.g. company posts, profile posts), so tool-selection guidance is only implied.

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