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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds substantial behavioral context beyond these: the participation loop (vote/review/comment on 3 launches), the boost object reporting progress, personalization rules (exclusions, tag-ranking), and the per-item indication of needed action (toggle_vote vs post_review). This goes far beyond the annotations and fully discloses behavior without contradiction.

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?

Though longer than average, every sentence carries distinct information: the feed's ordering and flags, the participation loop's mechanics, auth-specific behavior, per-item action hints, and boost progress. The most critical scoping (live launches needing attention) is front-loaded. No filler or repetition – it is information-dense yet efficient.

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?

Given the tool's complexity (personalization, participation loop, boost object) and that an output schema exists, the description covers all necessary call-time context: auth vs unauth behavior, what the feed contains, what each item indicates, and how the boost object works. Nothing an agent needs to decide whether and how to call 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% for the single 'limit' parameter, which is fully described in the schema ('Max results, 1-20, default 5'). The description does not add anything about limit semantics, which is fine because the schema already covers it. Baseline 3 applies; no additional value is provided or needed.

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 description opens with a specific verb+resource: 'Get engagement feed' and immediately defines its scope: 'Live FastDrop launches that need attention right now - fewest votes first, zero-review items flagged.' This clearly distinguishes it from sibling tools like list_launches or list_reviews, which are general listing operations. The participation loop and personalization details further cement its unique purpose.

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?

The description gives strong context on when to use it: for live launches needing attention, with a clear distinction between authenticated (personalized feed) and unauthenticated (generic feed) callers. It does not explicitly name alternative tools or state when not to use it, but the purpose is so specialized that the intended usage is unambiguous. Slight deduction for lacking explicit 'use X instead when Y' guidance.

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