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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower. The description adds real behavior beyond that: the output is raw Markdown, and ambiguous basenames resolve deterministically via an audience order. It omits not-found/error behavior, which keeps it from 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 short sentences, front-loaded with the return value, then input forms, then the edge-case rule. No filler and nothing that could be cut.

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 single-parameter read tool with no output schema, the description tells the agent what comes back (raw Markdown) and how inputs resolve. Only error/not-found behavior is unaddressed, a minor gap given the simplicity.

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 three accepted formats are already documented, but the description adds resolution semantics the schema cannot express — the audience precedence order used when basenames tie. That is meaningfully more than the schema provides.

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 — 'Return the raw Markdown source for a documentation page' — which immediately separates it from every sibling (pods, GPUs, balance, templates). The accepted input forms are named concretely with examples.

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 (read docs) but there is no explicit when-to-use/when-not statement or routing to a sibling such as 'search' for finding pages. The tie-breaking rule is genuine disambiguation guidance, but it only covers one narrow case.

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