doctor

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

With no annotations, the description carries the full burden. It usefully discloses the scope of checks performed, but says nothing about whether it mutates anything, requires specific access, or what the result looks like. The check enumeration is real value; the safety/mutation profile is absent.

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 parenthetical sentence that front-loads the verb and resource and packs the detail into a compact list. Nothing is wasted and nothing is buried.

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 two-parameter diagnostic tool with no annotations and no output schema, the description covers purpose but not behavior — no indication of whether it is read-only, whether it can auto-fix, or how to act on results. Adequate minimum, but incomplete for an unannotated tool.

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%, so both parameters are already documented in the schema. The description's phrase 'campaign or application' loosely mirrors the campaign/slug split, adding only marginal meaning beyond the structured fields. Baseline 3 applies when the schema does the heavy lifting.

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 ('diagnose') and two concrete resources (campaign or application) and enumerates the problem classes it detects (missing files, invalid frontmatter, toolhash mismatches). It is clearly distinguishable from data-reading siblings, though it never explicitly contrasts itself with 'repair', which is the natural fix-counterpart.

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 by the name and the enumerated issue types — you run it when you suspect something is broken — but there is no explicit when-to-use statement, no mention of when to use 'repair' instead, and no prerequisites. An agent can infer intent but is not guided.

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