scene_delta

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

With readOnlyHint=true already covering the safety profile, the description adds real value: the exact two-branch return shape and the notable fact that the unchanged path avoids leaking graph enumeration into the response. It does not address behavior on a stale or invalid hash, which keeps it below 5.

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?

Front-loaded with the core purpose, then the two return branches, then args. The Args section merely restates the schema description, which is mild redundancy but not bloat.

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, so the description's return-value disclosure is doing necessary work and covers both branches well. It is nearly complete for a one-parameter read tool, with error/stale-hash behavior the only gap.

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 single parameter's description is verbatim duplicated in the prose, so the description adds no meaning beyond the schema. Baseline 3 is correct.

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 verb+resource: comparing current scene state against a previous hash. It is clearly distinguishable from the digest-producing scene_digest, though it never names that sibling or diff_comp explicitly to route the agent.

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?

Describes the intended workflow: prev_hash comes from a prior scene_digest or scene_delta call, implying this is used to check whether anything has changed since a known snapshot. No when-not guidance or explicit alternatives are given, so it stops 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.