state_doctor

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

The annotations already declare readOnlyHint=true and openWorldHint=false, so "without modifying state" largely restates the annotation rather than adding new information. What the description does add is the specific class of anomalies it detects. It says nothing about what happens when problems are found — whether it reports them, fails, or how severity is conveyed — and idempotentHint=false is left unexplained.

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?

A single front-loaded sentence with no filler; the action, target, and scope of checks all appear before the trailing guarantee. Every listed check earns its place by narrowing what the tool validates.

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-only, closed-world inspection tool this is close to sufficient: it names the target and the checks. The one real gap is the absence of an output schema combined with no statement of what the inspection returns — a structured report, a pass/fail signal, or a list of findings — which matters for a diagnostic tool whose whole purpose is producing findings.

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 baseline is 4. There is nothing for the description to disambiguate, and it correctly avoids inventing inputs. It could still clarify that no target path is accepted (i.e. it operates on a fixed location), but that is a minor omission.

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 ("Inspect") and a specific resource ("agent state checkpoint files"), then enumerates the concrete defect classes it looks for (invalid JSON, key mismatches, byte-count drift, invalid timestamps, unexpected files). An agent can tell this is a diagnostic/validation tool rather than a read or write tool, though it never names or contrasts with the adjacent state_* siblings.

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 explicit when-to-use or when-not-to-use guidance. An agent choosing between state_doctor, state_read, state_list, and state_maintain must infer that this one is the non-mutating integrity checker from the phrase "without modifying state" alone. No prerequisites (e.g. must a checkpoint exist first?) are given.

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