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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely useful ecosystem-specific context beyond that: 'Read only, no lease' tells the agent this doesn't participate in the triage lease protocol that begin_triage/end_triage siblings use, which matters for sequencing. No return-format detail, but that is minor for a text-doc tool.

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 what the content covers, then when to read it, then the topic parameter. The middle sentence is a long comma-separated inventory that is dense but each clause maps to a real section, so it earns its place.

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?

A single optional-param documentation tool with no output schema; the description tells the agent what it will receive and when to fetch it. Nothing critical is missing, though it could state the return shape (markdown text vs structured) more explicitly.

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% and the enum carries its own description, so the baseline is a 3. The description adds value by naming the informational dimensions the sections map to (overview, why, when, routine, elevate, spam, tools), giving the agent enough to pick a topic without reading the enum more than superficially.

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 enumerates exactly what the tool returns (product story, why, when, routine, escalation rules, spam learning, tool-to-intent map), so an agent knows this is the documentation/orientation resource. It never names a sibling to differentiate itself, but the 'which tool serves which intent' framing makes its meta-role obvious against the operational siblings like triage or begin_triage.

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?

Explicit timing is given: read once at session start, or whenever the person asks what this can do, why, or how to get the most out of it. It also states the alternative invocation mode (pass `topic` for one section vs omit for all), leaving nothing to inference.

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