Explain a deferred deep link match

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

Annotations already establish readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description still adds behavioral context beyond that: it is a pure interpretive/offline operation that explains rather than computes, implying no network calls and deterministic output. It does not describe output format, but with annotations carrying the safety burden a 4 is warranted.

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?

Purpose and the decoded concepts are front-loaded in the first sentence, then two short sentences cover the accepted inputs and the offline trait. Every clause carries distinct information (what it explains, the inputs, the runtime behavior) with no 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?

There is no output schema, yet the description effectively previews the return content (meanings of score/quality, per-component breakdown, threshold guidance), which is exactly what an agent needs to know. Combined with the accepted input forms and the offline note, nothing needed to invoke and interpret it correctly is missing.

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% and the schema already documents each field, so baseline would be 3. The description adds invocation value by clarifying the three inputs are alternatives — pass the /sdk/match JSON, a DeferredDeepLink, or just a score — which explains why no parameter is required and how to choose among them.

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 names a specific verb (explains) and a specific resource (a DeepLinkNow fingerprint match result), and enumerates exactly what it decodes: confidence_score, match_quality, component scoring, and minConfidence threshold selection. No sibling (get_setup_guide, search_docs, list_links, etc.) does anything comparable, so it is trivially distinguishable.

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 clear context for use (interpreting a match result and tuning the SDK's minConfidence threshold) and even states the operational condition 'works offline'. It does not explicitly state when *not* to use it or name an alternative, which keeps it short of a 5.

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