search_tweets

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

Annotations already cover the read-only, idempotent, open-world profile, and the description goes well beyond them: it discloses the hydration pipeline and what fields it yields, the indexing lag on fresh posts, the search backend chain and the BRAVE_API_KEY auth requirement, and the speed cost of link resolution and enrichment. That is exactly the extra context annotations cannot carry.

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?

Core behavior and the recency caveat are front-loaded in the first two paragraphs. The third paragraph about matching OpenCode's keyless Exa/Parallel endpoints is backend trivia that does not help an agent decide or invoke, and could be trimmed.

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 9 parameters, an output schema, and full annotation coverage, the description supplies the needed mental model: index-based search, hydration output shape, latency knobs, and freshness limits. Minor gaps remain around pagination semantics (page vs limit vs sort) and how X operators combine with freshness, which the schema alone handles.

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 baseline is 3; the description earns an increment by explaining that results are hydrated into full text/author/date/metrics/media, which gives real meaning to the hydrate and enrich flags and their performance trade-off. Page/limit/sort interactions and the 1-9 page cap remain schema-only.

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 and resource ('Search X/Twitter posts') plus the mechanism ('through public web indexes'), and explicitly contrasts it with X's live search, which separates it from get_tweet/get_user_tweets-style tools. It never names a sibling as the alternative, so differentiation is by implication rather than explicit routing.

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?

Usage context is implied rather than prescribed: the note that very recent posts may not be indexed hints at when this tool will under-perform, but there is no explicit 'use get_user_tweets for a timeline' or 'use get_tweet when you already have an ID'. The backend/fallback narration describes internals, not selection guidance.

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