tv_setup_doctor

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

With readOnlyHint=true, the annotation already indicates safety, but the description goes well beyond that by disclosing the exact output shape ({name, ok, detail, optional}), the presence of a `fix` field, and the required workflow after running fixes. It also transparently states that credential checks always require a human and must not be attempted automatically. This is rich behavioral disclosure that complements the annotations without contradicting them.

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?

The description is compact and front-loaded with the core purpose. Each sentence adds distinct value: first the diagnose-and-fix purpose, then the output contract, then the remediation workflow, and finally the credential-handling caveat. There is no filler or repetition.

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 diagnostic tool, the description covers everything an agent needs: what the tool does, what it returns, how to use the results, and which actions require human involvement. The presence of an output schema reduces the need to document return values further, and the description already summarizes the key output fields.

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 has zero parameters, so there is nothing for the description to explain about parameter usage. The description instead focuses on the diagnostic workflow and output contract, which is the most relevant semantic content for this tool. The baseline of 4 for no-parameter tools is appropriate.

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?

The description opens with a concrete action: 'Diagnose this install: check every prerequisite, return exact fixes.' This clearly identifies the tool as a setup diagnostic, distinguishing it from siblings like tv_screener_run or tv_data_get_bars, which perform different functions. A specific resource ('this install') and expected outcome ('return exact fixes') makes the purpose unambiguous.

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?

The description gives explicit workflow guidance: run fixes for anything with ok=false and optional=false, rerun the doctor, and the install becomes operational. It also warns that credential checks are optional and require human involvement. It does not explicitly compare against sibling tools, but the usage context is clear enough that an agent would know when to invoke it.

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