cite

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

With no annotations, the description carries the full burden and does well: it discloses validation rules (0 <= start < end <= len(text)), a length cap, and the side effect of recording an EvidenceEntry. It does not cover failure/error behavior or any permission requirements, which keeps it short of 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?

A single dense sentence that front-loads the core action, followed by validation and side-effect details. No filler, though the validation clause is packed tightly enough that it reads a little heavy.

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?

An output schema exists, so return format need not be explained, and the description still notes it returns an EvidenceEntry. For a two-parameter nested-object tool with no annotations, the validation and side-effect disclosure makes it nearly complete; only error handling is absent.

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 50% (the span object is documented, url is not), and the description compensates by spelling out the valid offset range and the constraint that the page must be stored. That adds real meaning beyond the schema's terse 'Character offsets into page.text.'

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 ('Convert...into a citation') and a specific resource ('an inspected span of a stored page'), which is far more than a restatement of the name. It is clearly distinct from siblings like search/read/grep, though it never explicitly names a sibling it is not.

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 phrase 'an inspected span of a stored page' implies a precondition (the page must first be inspected/read), which hints at when the tool applies. However, there is no explicit when-to-use, when-not-to-use, or routing against siblings such as read or corpus_search.

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