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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description goes well beyond that: it discloses that a single like creates a lead, that icp_score is ContentIn-computed from a headline rather than verified data, that classified:false with icp_score:null means 'not scored yet' rather than 'poor fit', that icp_score_source='user_override' is the user's own label, and that sorting keeps computed position while reporting the override number. These are exactly the interpretive pitfalls an agent would otherwise get wrong.

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?

Purpose is front-loaded, followed by the REACTIONS and SCORE clarifications, which is the right order. It is a long description and the icp_score explanation sprawls across several sentences with some restatement, but each block addresses a distinct misinterpretation risk rather than padding.

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 an 8-parameter, all-optional, paged list tool with no output schema, the description covers return fields, ordering behavior, scoring provenance, paging scale and the default status filter's exclusion of dismissed leads. Nothing an agent needs to call it correctly or report results accurately 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 the schema carries the field-level burden and the baseline is 3. The description still adds genuine semantics the schema does not: the ordering-by-icp_score divergence between computed score and reported override value, and the paging scale ('thousands of leads'), which explains why before/before_id exist.

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?

Opens with a specific verb+resource and immediately scopes it: leads are people who engaged with THIS user's own posts, with an enumerated return fields list (name, headline, profile, engagement type, comments, posts, icp_score). This cleanly separates it from siblings like list_my_comments and list_posts, which concern the user's own comments and posts rather than other people.

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 three concrete usage scenarios ('who is engaging with me', finding warm contacts, judging which posts attract the right audience) and states the paging expectation for large result sets. It does not name adjacent sibling tools or state when NOT to use it, so it is clear context without explicit alternative routing.

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