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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: result ordering matches request order, each item carries ok plus document or error, and one failure does not suppress siblings. It says nothing about taint_mode, include_tainted, or include_unverified, which materially change what is returned.

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, no filler, with the batch cap and key shape front-loaded. The trailing line break and sentence fragment for the partial-failure note is slightly unpolished but not wasteful.

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 the results[]/ok/error explanation is supportive rather than required, and the request-order guarantee adds real value. However, for a six-parameter tool with zero schema prose, leaving the three taint-related parameters undocumented is an incompleteness an agent will feel when reading untrusted documents.

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?

With 0% schema description coverage, the description carries the full burden and covers only three of six parameters: uris, keys (with its object shape), and fields. taint_mode, include_tainted, and include_unverified are left entirely unexplained despite the enum on taint_mode and the security-relevant defaults (annotate, false, false).

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 gives a specific verb (Resolve) and resource (L2 URIs or keys in {namespace, doc_key, version} form), plus a batch bound of 25. It is clearly the bulk form of the sibling 'dereference', but it never names that sibling explicitly, so the differentiation is implied by the name rather than stated.

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?

There is no guidance on when to pick this over 'dereference', nor on whether uris and keys are alternatives or can be combined, nor on what happens when both are null. The one usage-flavored statement ('One failed URI does not hide successful items') describes failure behavior rather than selection criteria.

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