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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes well beyond that, disclosing the approval queue state machine (pending_approval vs auto-send), the deduped outcome, that it resolves a URN and creates a linkedin_invite_queue item, and explicitly tells the agent to relay the returned message rather than promise a review.

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?

Front-loaded with the summary and the key approval caveat, and organized into returns/behaviour blocks. It is somewhat verbose and repeats the comment/reaction exclusivity and reaction list already in the schema, costing a little efficiency.

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 7-parameter mutation tool with no formal output schema, the inline <returns> block covers all three outcome shapes (success, deduped, error) and the approval semantics are explained end to end, so an agent has everything needed to call it and interpret results.

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 mutual-exclusivity rule and reaction enum are already documented there. The description still adds meaning by specifying the agent should default to reaction_type='like' and by tying prospect_identifier to the warm-up counter behavior, which the schema only partly conveys.

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 ('Queue') and resource ('an engagement (comment or reaction) on a LinkedIn post'), and the name/purpose cleanly separates it from the read-side sibling query_linkedin_post_engagements. An agent can tell what this does without opening the schema.

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?

Gives strong when-to context: default is pending_approval unless auto-approve is enabled for the linkedin_comment/linkedin_reaction subtype, 'like' is the default reaction the agent should pick, and prospect_identifier is required for warm-up flows but safe to omit otherwise. It stops short of naming an alternative sibling tool to use instead (e.g. the query counterpart), so it is not a full 5.

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