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

Beyond the readOnlyHint/openWorldHint/destructiveHint annotations, it discloses concrete runtime behavior: auth modes (app-token vs B2B with explicit appId), error codes (401/403 wrong auth, 404 unknown appId), the empty-list result when nothing has been uploaded, and the fact that existing docs carry RAG tags. This is exactly the kind of operational detail an agent needs that annotations alone cannot convey.

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 short sentences, each earning its place: purpose+returns, downstream consumers, auth/error contract, and the sibling equivalent. Front-loaded with the core function and free of filler or duplicative title repetition.

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?

Given one optional parameter, high schema coverage, and no output schema, the description covers what an agent needs to operate it: what it returns (documents with id/name/RAG tags), how authentication determines whether appId is required, error/empty-list outcomes, and what to do with the results. There is no significant operational gap.

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% for appId (24-char hex, required in B2B unless set via ethora-app-select, ignored in app-token mode), so the schema carries the parameter burden. The description reinforces the auth-mode dependency of appId but adds no fundamentally new semantics, matching the baseline of 3 for complete schema coverage.

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 specific verb+resource: "List an app's ingested documents," and immediately specifies the returned fields (id, name, current RAG tags), so an agent knows exactly what comes back. It also differentiates this read-only docs listing tool from its downstream mutation siblings (tags-update, delete) and the website-source counterpart (ethora-sources-site-list-v2).

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?

The description explicitly explains when the tool is useful – it is the source of document ids consumed by tags-update-v2 and delete-v2 – and names the website-sources alternative (ethora-sources-site-list-v2), routing an agent to the right sibling. Auth mode selection and behavior with/without appId are covered, though it never states an explicit 'use this instead of X when...' exclusion phrase.

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