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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=true, openWorldHint=true), and the description adds substantial context beyond them: the sandbox blocks fetch()/WebSocket for undeclared hosts, Muninn's own hosts are refused here, the whole list is replaced, and a published artifact's public copy updates in the same call. It also surfaces two non-obvious consequences an agent could not infer — the list is shown to every reader of the page, and the host must answer Access-Control-Allow-Origin: * because the frame origin is null.

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-loads the verb+resource and the primary use case, then layers constraints and warnings in descending priority. It is a single dense paragraph running long, and the CORS/key-mirror digression could be split or trimmed, but nearly every clause carries actionable information and nothing is padding.

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?

Even with no output schema, the description names the return shape ({success, artifactId, connect}) and covers hostname format, count limit, clearing behavior, public-copy propagation, and failure fallbacks. An agent has everything needed to call this correctly on the first attempt without discovering the sandbox rules by error.

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 contributes real constraints the schema does not encode: bare lowercase hostnames only, no scheme, path, port, wildcard or IP, and a security rationale for declaring 'exactly what the source calls and nothing more.' It also restates the [] / null clearing semantics with the consequence ('returning the artifact to Muninn-only fetches').

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?

Opens with a precise verb triple and resource: 'Declare, change or clear the outside hosts an html/svg artifact may fetch data from at runtime.' This is unmistakably distinct from siblings like muninn_artifact_add, muninn_artifact_publish, or muninn_mirror_connect, and names its own scope (runtime fetch allowlist) rather than a generic artifact edit.

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?

Gives three concrete triggers (a dashboard/chart reading an external API, the user saying 'let it load live data from X', or muninn_artifact_add warning that a host is undeclared) and an explicit exclusion ('Not needed for <script src>, images, fonts or styles from a CDN'). It also routes to an alternative (mirror the data into a Muninn json/csv artifact and fetch /raw) when CORS or a key blocks direct fetching.

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