self_test

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

Adds real context beyond the annotations: the call executes other tools (openWorld-ish side effects), persists a baseline when none exists, and deliberately excludes write/file tools. The description's 'Saves a baseline' explains why readOnlyHint is false despite the read-only framing, which is exactly the kind of disclosure annotations can't convey alone.

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?

Four short sentences, front-loaded with the core action, followed by scope and the baseline override. No filler; the first sentence is slightly dense but every sentence carries a distinct fact.

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 meta-tool with no output schema, the definition covers intent, scope, and the baseline write, but leaves two gaps: what `profile` selects and, critically, what the comparison returns (pass/fail, diff detail, per-tool results) an agent needs to interpret the outcome.

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 description coverage is 0%, so the description carries the full burden, and it only explains one of three parameters ('Set update_baseline to accept the current structure as the new baseline'). The required `service` and especially `profile` are left entirely undefined in both schema and description.

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 and resource: run a service's read tools and compare each answer's structure against a saved baseline, plus save baselines where none exist. The verb+resource is concrete and unlike anything the siblings (list_services, forget_session, logout) do, though it never names or contrasts those siblings directly.

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: this is a verification/regression-check tool, and the sentence 'Write and file tools are not run' scopes it to read paths. It also implies the update_baseline flow, but there is no explicit 'use this when…' or guidance on when to self-test vs. just calling the tools directly.

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