X (Twitter)

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

Beyond the annotations (readOnly/openWorld/idempotent/non-destructive, all consistent with a pure-read tool), the description discloses a per-resource credit price schedule, that failures are free, that cached reads cost 0 credits, that list resources return a cursor, and a non-obvious tiered pricing model for AI transcription with an allow_long_transcription opt-in. These are exactly the cost and side-effect facts an agent needs before spending credits.

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?

Front-loaded with the dispatch rule and pricing/paging rules, then a tight one-line-per-resource table with credit cost and a 'Paged' marker. Every sentence carries operational information; no filler or restatement of the tool name.

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 an 8-parameter dispatcher with a nested free-form `params` object and no output schema, it covers resource selection, argument placement, pagination, caching, and cost. The remaining gap is the response shape for the returned data itself (what a profile or post object contains), plus how pagination terminates, which the description leaves 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, but the description adds the dispatch convention that resource-specific parameters live at the top level while anything else goes in `params`, and ties cost behavior to max_age_days. It also flags allow_long_transcription as an optional parameter for tweet.transcript, though it defers most optional-parameter types and allowed values to a separate describe call.

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 ('Data from X (Twitter)') and then enumerates seven named resources (community, community.tweets, profile, profile.tweets, search.posts, tweet, tweet.transcript), each with its identifying argument. This immediately separates it from the platform siblings (youtube, tiktok, instagram) and from generic siblings like get_post or search, which return different data sources.

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 explicit operating instructions: pick a resource, pass that resource's parameters as top-level arguments, put extras in `params`, reuse `cursor` for paging, and use max_age_days for a free cached copy. What it does not do is state when to choose this tool over overlapping siblings such as get_profile, get_post, search, or get_transcript, nor when not to use it.

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