Resolve References Batch

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

With only readOnlyHint=true in the annotations, the description carries real behavioral weight: it discloses that no additional network requests are made, that results are truncated by JSON order rather than relevance, that images/media are excluded, and that output is grouped by kind. That is substantive context beyond the annotation, though it stops short of covering failure modes or invalid-URL behavior.

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?

It is a single dense sentence with parenthetical asides, but the core purpose is front-loaded and the trailing clauses (ordering, exclusions, filter) each add distinct information. Slightly over-packed for one sentence, but no clause is filler.

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?

With no output schema, the description must describe the return shape, and it does: title, kind, Apple's summary, and declaration for symbols, grouped by kind. Combined with the ordering and exclusion notes, an agent has enough to call and interpret the tool, with only error/edge-case behavior left unstated.

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%, so the baseline is 3, but the description adds meaning the schema does not: maxReferences is explicitly ordering-semantic ('the first maxReferences in the JSON's own order, not by relevance'), and filterByType is characterized as keeping 'one role or kind'. Those are genuine semantic additions rather than restatements.

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 states a specific verb-resource pairing: it returns the pages that a given documentation page references, scoped explicitly to what is derivable 'from that page's JSON alone (no further requests)'. This clearly separates it from the sibling search_* and browse_* tools, though it never names an alternative directly, which keeps it short of a 5.

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?

Usage is implied rather than stated: the agent can infer it should call this to enumerate a page's outbound references, and it gives ordering/limit guidance ('first maxReferences in the JSON's own order, not by relevance'). However, there is no explicit when-to-use versus search_apple_docs or get_apple_doc_content, nor any stated exclusion or prerequisite condition.

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