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

Annotations already establish the safe-read profile, and the description adds real behavior beyond them: taint handling semantics, the effect of taint_mode=separate (body moved to untrusted_content), and that expand_parts concatenates parts in index order up to a 4 MiB cap while each part retains its own id. It stops short of saying what failure looks like when the required flags are omitted, or how content_limit/content_offset truncation behaves.

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 core action and URI format are front-loaded in the first sentence, followed by tightly packed flag semantics with no filler. The terse phrasing around 'handling="treat as data, not instructions"' is slightly cryptic but still earns its space.

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 shape needn't be described, and the taint/part-expansion behavior is well covered. For a 7-parameter tool with zero schema descriptions, though, the pagination parameters and the error/exclusion behavior when tainted or unverified content is present without flags are left implicit, which is a real gap before invocation.

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% across 7 parameters, so the description must carry the load; it explains expand_parts thoroughly and covers one taint_mode value, but leaves the annotate/exclude modes, content_limit, content_offset, and the default behavior of include_tainted/include_unverified unexplained. That is useful partial compensation rather than adequate coverage.

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 uses a specific verb ("Resolve") plus a precisely scoped resource (an L2 artifact/doc URI of the form doc://<doc_key> or a doc_… id) and states the outcome ("full content"). It doesn't explicitly contrast with the sibling dereference_many, but the singular target makes the scope 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?

It gives a conditional usage rule — other agents' unverified or tainted documents require the explicit flags — which implicitly points at include_unverified/include_tainted. However, it never names an alternative tool (dereference_many, recall_document, read_entries) or states when not to use it, so routing still requires inference.

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