infomaniak_docs_read

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses the return shape (source, retrieval time, steps/links), the presence of explicit pagination, that no provider token or browser cookies are required, and a guardrail against bypassing denied scopes, pending approvals or locks. With no output schema, this carries useful weight, though it does not explain how pagination terminates or how next_offset relates to expected_sha256.

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-loaded with the action and resource in the first sentence, followed by return-shape and then policy constraints, with essentially no filler. The final sentence reads as a guardrail more than a behavioral fact about this tool, but it is short and relevant.

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 read-only fetcher with no output schema, the description supplies the essentials: what is fetched, what is returned, that paging exists, and that no credentials/cookies are involved. The remaining gap is operational detail on pagination continuation, which an agent would otherwise have to infer from the parameter names.

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 only 50%: url and expected_sha256 are documented, while offset and max_chars have no descriptions anywhere except name, default and bounds. The description's mention of "explicit pagination" signals that paging exists but does not define offset/max_chars semantics or the next_offset round-trip, so it only partially compensates for the coverage gap.

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 concrete verb ("Fetch") and a precise resource ("current official help article or developer API reference"), which an agent can distinguish from the sibling search tool by the verb alone. It stops short of naming infomaniak_docs_search as the discovery counterpart, so differentiation is implied rather than explicit.

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 context is implied rather than spelled out: the schema's url field says the URL comes "from search", and the description adds a fallback path ("Use the guide with your own authorized browser/computer tools when an API capability is missing") plus prohibitions on bypassing scopes/approvals/locks. There is no direct when-to-use-this-vs-siblings statement such as 'call docs_search first to obtain the URL'.

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