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

Beyond the readOnly/idempotent/openWorld annotations, it discloses the cost model (1 request per data type, boards 1 request per 10 rows), that only answering data types are charged, that the response reports requests_charged, and that a plan-limit message comes back on rate limit or quota exhaustion. That is meaningful operational context annotations cannot express. It stops short of describing ordering, freshness windows, or empty-result behavior, which keeps it from a 5.

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 most discriminating information — what it returns and how it differs from the measure siblings — is front-loaded, and the cost/failure sentences are load-bearing rather than filler. It is dense and runs long as a single block, which slightly hurts scanability, but no sentence is expendable.

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 multi-source, cost-accruing read tool with no output schema, it covers return contents, per-source engagement fields, cost accounting, the charged-only-for-answering rule, and the rate-limit/quota failure mode. An agent has everything needed to call it correctly and predict the billing consequence.

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 baseline is 3; the description adds value by tying cost to specific parameter choices ('all' costing 10, boards per 10 rows) and by clarifying that hashtag mode applies only to TikTok and Instagram while other sources fall back to keyword search. The remaining parameters (days, limit, comments) get no extra meaning beyond the schema.

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 concrete verb+resource statement ('What people are posting, reading and betting about a keyword right now') and enumerates the returned artifacts (posts, videos, news stories, discussions, prediction markets) plus the hashtag mode. It explicitly distinguishes itself from the sibling measure tools, so an agent can separate it from get_time_series and get_growth without reading schemas.

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 states the use case ('explain why something is trending or what the conversation says') and names the alternatives with the condition that selects them ('get_time_series and get_growth measure how much'). The hashtag=true branch is also framed as a distinct mode of use, so when-to-use and when-not-to-use are both covered.

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