doctor

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

With no annotations, the description carries the full behavioral burden. It conveys a read-only diagnostic intent ('Diagnose') and details what is inspected: SDK path, tools, AVDs, devices, accessibility bridge status, and build tools. It does not explicitly promise zero side effects, but 'diagnose' and the absence of any fix/update language strongly imply it is a non-mutating inspection.

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 dense but well-organized: it front-loads the purpose, uses a colon to launch the checklist, and adds an em-dash rationale for the gradle requirement. There is minor repetition between 'first call of any session that isn't going well' and 'Run this first when something isn't working', so it is not maximally tight.

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 diagnostic tool, the description is complete: it tells the agent when to run it, what subsystems it inspects, and even explains why a system gradle matters. No output schema exists, but the enumerated diagnostic areas give sufficient context for what kind of results to expect.

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 and an empty schema, so there is nothing for the description to explain. The description correctly does not invent parameters, and the 0-parameter baseline of 4 applies because no semantic gap exists.

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 specific verb and resource: 'Diagnose the local toolchain' and then enumerates exactly what is checked — SDK path validity, adb/emulator availability, AVDs, devices, accessibility bridge, JDK, and system gradle. This clearly distinguishes it from sibling tools like list_devices or list_avds because it is an aggregated diagnostic rather than a single-feature listing.

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 explicitly says to run this tool first when something isn't working, and gives a concrete trigger: a Gradle tool failing with 'SDK location not found'. It does not name alternatives or exclusion cases, but for a diagnostic first-stop tool this context is clear enough.

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