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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), and the description adds genuinely useful behavior: fuzzy matching, billing on successful empty results, and that result_count is a retrieval-window count rather than a match total. However, the pricing statements conflict with each other — 'One credit per successful request' versus 'Completed lookups cost at least 10 Nexscope credits' — which makes the actual cost behavior unreliable for the agent.

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?

The core paragraph is repeated almost verbatim a second time, with a stray 'Cosmos Search API View Pricing' fragment spliced in mid-text and a boilerplate pricing block that contradicts the earlier per-request cost. Useful signal exists but is buried in duplication an agent must read past.

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, the description does explain two response fields (has_more, result_count) and pagination termination, which is the right instinct. But it never characterizes the shape of a post record or the other fields returned, and the muddled credit statements leave the cost model ambiguous for a paid, per-request tool.

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% and the cursor parameter is already documented in the schema down to the literal "null" terminal-page trick, so the description adds little on inputs. Its one real contribution is interpreting result_count, which is a response field rather than an input, leaving input semantics essentially as the schema states them.

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 opening states a specific verb and resource: 'Search public Cosmos posts by keyword', plus the useful caveat that Cosmos may return related posts without an exact match. It never names a sibling (e.g. social_cosmos_post or social_cosmos_user_posts) to sharpen the boundary, but the verb+scope is still distinguishing enough to pick the right tool.

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?

It gives concrete operating guidance: keep the cursor unchanged, stop when has_more is false, and sending cursor=null yields a zero-cost terminal page. It stops short of naming alternatives, so an agent has to infer that profile/post/cluster lookups are the non-search route.

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