scene_digest

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

With readOnlyHint=true already covering the safety profile, the description adds a genuine behavioral trait: output is stable across no-op turns, which is exactly the property an agent needs for delta-based caching. It does not cover cost, rate limits, or error behavior, but the added determinism note is substantive.

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?

Two short sentences with no filler; the payload contents come first and the scene_delta pairing second. The mid-sentence line break hurts readability slightly but wastes no words.

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?

For a zero-parameter read tool with no output schema, the description effectively substitutes for a return-value spec by enumerating the fingerprint's fields. It leaves the exact shape (e.g., how counts are keyed) implicit, but an agent has enough to decide and invoke.

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?

The tool takes zero parameters, so the schema carries nothing to document and the baseline of 4 applies. Nothing in the description contradicts or duplicates a parameter contract.

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 resource (the script's scene) and enumerates the exact contents of the fingerprint (counts by class, errors, warnings, selection, active viewer, display node, md5 hash), and it explicitly names the sibling scene_delta as the paired tool, so it is distinguishable without opening a schema.

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?

"Pair with scene_delta to skip re-rendering large response payloads when nothing has changed" gives clear context for when this tool's output is useful, and the no-op stability property hints at the polling use case. It stops short of an explicit when-not-to-use statement or listing other alternatives among the many read_* siblings.

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