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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond them: it explicitly says the tool "opens nothing by itself" and that execution requires a separate browser step, plus the constraint that Slab's GraphQL API is Business/Enterprise only. It does not describe error behavior or what happens if the user lacks a Slab Cloud Browser session.

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 core workflow is front-loaded in the first two sentences, but the phrasing is padded — "from ChatGPT, Claude or any AI agent" adds nothing about behavior, and the trailing "checked 28 Oct 2026" API note is a tangent that dilutes the actionable content. Semicolon-chained clauses make the actual contract harder to parse than necessary.

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 carries the burden of explaining returns, and it does partially ("step by step (screens, buttons, fields)"). However, it never resolves whether expired posts themselves are returned or only instructions for finding them, and it omits what to do if the described screens don't match. For a zero-param tool this is adequate but leaves a real ambiguity.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the empty schema is fully consistent with the stated behavior. Baseline of 4 applies for a no-parameter tool, with no misleading parameter language.

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 names a specific verb and resource ("List expired posts") and scopes it to "the user's own Slab account." It then pivots to say the tool actually "Returns how to do it in Slab step by step," which muddies whether the tool lists posts or returns instructions — the agent must read both sentences to understand the real output. It never contrasts itself with sibling slab_search_posts, so differentiation is left to the name.

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 is implied through the workflow: call this, get steps, "then do it with the cotlet_browser_* tools in the user's Slab Cloud Browser." That is useful sequencing, but there is no explicit statement of when to prefer this over slab_search_posts or other Slab siblings, and no stated preconditions beyond the API-plan note.

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