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

Annotations carry only readOnlyHint=true, so the description does the heavy lifting — and it does it thoroughly: response invariants (total_posts_stored always included), pagination contract (has_more → next_offset → offset), field semantics (like_count is thumbs-up alone vs total_reaction_count is all types), and default ordering behavior. No contradiction with readOnlyHint since this is clearly a fetch operation.

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?

Long but information-dense — every sentence earns its place (routing, examples, field meanings, pagination). Slight redundancy in restating sort='top' ('their best-performing with sort=top' then 'sort=top is what answers...') but that repetition serves a routing purpose. Core purpose is front-loaded before alternatives and edge details.

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 list tool with no output schema, the description fully covers the agent contract: row content, engagement field meanings, sort semantics, response invariants (total_posts_stored, has_more, next_offset), and pagination. An agent can select, sort, and page through results without ambiguity; nothing needed for correct invocation 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 3 applies. The description adds real value on top: it maps sort='top' to natural-language queries ('my best posts', 'what performed well'), clarifies when sort='oldest' is the right choice (start of posting history), and explains the offset paging contract (call again with offset set to next_offset). This exceeds baseline but the schema already documents the enum and each parameter well.

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 ('The user's own LinkedIn posts') plus what's included (engagement numbers: reactions, likes, comments, shares). Explicitly contrasts itself with the closest sibling, linkedin_analytics, and is clearly distinct from get_my_tweets (platform-specific). An agent can tell exactly what this tool returns and how it differs from similar ones.

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 routes traffic: 'Answer those from here rather than from linkedin_analytics, which needs an OAuth grant this user may not have given.' Gives concrete query phrasings that should be answered here ('my top 10 posts', 'what did I post last week?', 'how many posts do I have?') and instructs the agent to compute averages and comparisons from returned rows. Also states the exclusion condition (OAuth grant) with reasoning.

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