Capture X post

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description supplies the missing specifics: recapturing can replace the saved corpus and metadata, disabled capture or extraction failure returns an error. It also discloses the return payload (item ID, title, captured-tweet count, metadata) even though no output schema exists, so the agent knows what a successful call yields before invoking it.

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?

Four dense sentences with no filler: purpose first, then sibling routing, then prerequisites, then return/destructive behavior. Every sentence carries decision-relevant information an agent would otherwise have to guess.

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 single-parameter, no-output-schema mutation tool, the definition covers purpose, routing, prerequisites, success payload, error conditions, and overwrite semantics — close to complete. It stops short of saying what happens on partial extraction (e.g., some tweets captured, others not) or whether corpus replacement is all-or-nothing.

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?

With one parameter at 100% schema coverage, the schema already explains that the URL must be a public x.com/twitter.com status URL for the terminal post in the desired author chain. The description only adds the "public source access" requirement and the chain framing, which largely duplicates the schema wording. Baseline 3 is appropriate.

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 — "Capture an X post and its author's earlier chain as a local text corpus item" — including the non-obvious scope that it pulls the author's prior thread, not just one tweet. It explicitly distinguishes itself from uoink_url (video) and uoink_page (general webpage prose).

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?

Names two alternative tools and the exact condition that routes to each ("use uoink_url for an X video capture or uoink_page for general webpage prose"), which is precisely the decision an agent faces among the uoink_* siblings. It also states a prerequisite (x_text_capture_enabled and public source access) that gates whether the call should be attempted at all.

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