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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds meaningful behavioral details beyond annotations: the tree is 'navigation-v1', warnings indicate uncertain structure, and citable=false marks navigation containers or unverified fragments. This informs the agent about output nuances without contradicting the annotations.

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?

The description is compact—three sentences with no fluff. It front-loads the core purpose and then adds supporting details about hierarchy encoding, warnings, and the citable flag. However, the jargon 'navigation-v1' is somewhat opaque and could be simplified or defined, slightly reducing clarity.

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?

The tool has an output schema (not shown) which relieves the description of explaining return values. Yet the description omits guidance on the document parameter, potential error conditions, or how to obtain the initial document id. For a read-only tool with one parameter, this is a notable gap that affects completeness.

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 0%, and the description fails to explain the 'document' parameter beyond its type. It does not clarify what format the document identifier takes, what a valid input looks like, or how it relates to the returned tree. With zero schema coverage, the description was expected to compensate but does not, leaving the agent to guess the parameter's meaning.

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 clearly states the tool returns a 'compact navigation-v1 tree of indexed source text' and elaborates on depth/path encoding and metadata sharing. This distinguishes it from sibling tools like search or fetch, which have different purposes. The verb 'Return' plus the resource and key characteristics make the purpose unambiguous.

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 implies this tool is for obtaining an outline/tree of a document but does not explicitly state when to use it versus siblings such as find_exact_text or search. It mentions 'Pass opaque ids unchanged to fetch' which hints at integration with fetch but offers no explicit exclusions or conditions. The context is present but not framed as guidance.

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