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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely non-obvious value beyond that: the data-quality caveat that posts are unverified claims rather than news confirmation, which affects how an agent should weight results. Return format and rate limits are still unstated.

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?

Three short sentences with no filler: capability first, then the selection cue, then the reliability caveat. Every sentence carries a distinct piece of information.

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 weak schema coverage, the description carries more of the load. It covers query semantics, sorting, and the trust caveat, which is a reasonable core, but leaves the default/capped time window and result-count parameter behavior to the schema.

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 only 25% (only `hours` is documented in the schema), so the description must compensate. It usefully explains what `query` accepts (phrase, cashtag, handle, advanced X query) and maps the Latest/Top ordering to `queryType`, but says nothing about `limit`, the 72-hour default window, or the 336-hour ceiling.

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 (Search) and resource (the X/TWIT feed) plus the accepted input forms (phrase, cashtag, handle, advanced query) and the sort modes. It is distinguishable from social.ticker_posts, but that sibling is never named, so the differentiation rests on inference.

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?

"Use when a company name or event is not captured by its cashtag" gives a concrete trigger condition that implicitly routes to the cashtag/ticker-oriented sibling. There is no explicit when-not or named alternative, but the context is clear enough to choose correctly.

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