Trending developments

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

Annotations already declare readOnly/idempotent/openWorld, so the description's added value is the cost/shape warning that the slot list is long and should be narrowed, plus the item content (source counts, sentiment counts, newest statement). With no output schema, disclosing the `trending` vs. `trending_labels` distinction and the `total` field is genuinely useful. It stops short of pagination or ordering edge cases.

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 purpose is front-loaded and every topic is relevant, but the body interleaves kind semantics, return-shape detail, an alternative-tool pointer, and item field definitions without clear ordering. The trailing fragment 'symbol: one code only.' reads as an orphaned patch rather than intentional structure.

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 steps in to explain the returned fields and the `total` indicator, which is the main gap it needed to fill for a 4-parameter read tool. Behavior of conflicting filters (symbol plus theme_id) and how `limit` interacts with `total` are left implicit.

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, and the description goes beyond it by advising which parameters to use to avoid pulling the full slot list and by noting symbol accepts 'one code only'. The `kind` semantics in the description largely restate the schema's own enum descriptions, so the gain is modest rather than transformative.

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 the resource and scope precisely: 'The developments most outlets are reporting', plus a plain-language gloss ('what is moving / what is the big news right now'). It also differentiates the two modes (live list vs. top of each recent slot). The only softness is that 'developments' is a domain term never defined, so an agent must infer it from the described item fields.

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?

Gives an explicit use case ('what is moving right now'), an explicit alternative with the condition that selects it ('For a whole day rather than right now, use find_topics with sort=velocity'), and a scoping instruction ('narrow it with symbol or theme_id rather than asking for all of it'). All three when/when-not/alternative dimensions are covered.

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