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

Goes well beyond the annotations by disclosing a per-user rate limit ('one refresh per user every five minutes across instances'), batch caps (100 posts, 50 videos), early termination under a time budget with 'skipped' counts, a cooldown before individual re-refresh, and result semantics ('missing metrics are not zero performance'). This is rich operational context that annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) cannot express.

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-loads the core action in the first two sentences, then layers constraints and post-refresh guidance. It is information-dense rather than padded, though the run of caveats (batch, timeout, cooldown, rate limit, result semantics) makes it longer than a minimal definition.

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 and a state-changing, rate-limited, open-world operation, the description supplies most of what an agent needs to call it correctly, including limits and partial-completion behavior. It stops short of describing auth/permission requirements or the precise response shape beyond 'successes and failures'.

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 0%, so the description must carry parameter meaning. It conveys the concept of targeting 'one post or video' and that omitting a target triggers a batch refresh, which maps loosely to postId/postType. But it never names the fields, the uuid format, or the enum values ('post'/'video'), leaving the schema to do the rest.

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 ('Refresh') and resource ('social performance data' / 'platform metrics') and clarifies scope: single post/video or a bounded recent batch. This clearly distinguishes it from read-oriented siblings such as getAnalyticsOverview and getPostAnalytics.

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?

Describes the two targeting modes (single item vs. bounded batch) and adds a follow-up path ('Refresh those posts individually after the cooldown'). However, it never names a sibling tool to distinguish this refresh action from the read-only analytics retrieval tools, so the when-not guidance is implied rather than explicit.

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