invoke_capability

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

With no annotations, the description carries the full load and does so well: it discloses that verified T1/T1b capabilities hit the service's real web API inside the authenticated session, that guarded/catalog-tail hits return typed pending/fallback responses, and that mutating capabilities produce real side effects. It omits reversibility/idempotency and rate-limit behavior, so not a 5.

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?

Three tightly packed sentences, front-loaded with the core action and followed by behavior and error handling; every sentence earns its place. The density of T1/T1b and RECIPE_* jargon slightly taxes readability but does not waste space.

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?

There is no output schema, and the description compensates by explaining the kinds of results returned (structured result vs typed pending/fallback) and the exact recovery action for each fallback code. For a dispatch tool with zero annotations, nothing essential to a correct call is missing.

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 description coverage is 100%, so the schema already documents slug, params, and tab_id. The description only restates that the slug comes from a search_capabilities hit and params must match the hit's JSON-Schema, adding no syntax or format detail beyond structured data. Baseline 3 applies.

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 ('invoke a capability by slug') and ties the input source to a named sibling ('from a search_capabilities hit'). An agent can immediately distinguish this from the DOM/action siblings because it names both the operation and the feeder tool.

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?

Routing is explicit: get the slug from search_capabilities, check the side-effect class before mutating calls, and switch to DOM tools when RECIPE_DOM_FALLBACK_PENDING / RECIPE_LEARN_PENDING / RECIPE_EXPIRED are returned. It lacks a crisp when-not-to-use statement (e.g., prefer direct click/type for one-off actions), so it falls short of the top band.

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