Local models

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds context beyond them: dependency on Ollama being reachable, the LLMxRay dependency for the machine line and its graceful omission, the cost profile (well under a second, two listing calls, no model loaded), and the snapshot/keep_alive staleness caveat. That is unusually rich behavioral disclosure that does not contradict the annotations.

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?

Front-loaded with the capability, then boundaries, then return format, then operational caveats — a sensible order with no filler sentences. It is long for a no-arg tool, but nearly every clause carries distinct information (dependencies, cost, staleness), so the length is mostly earned rather than padding.

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?

With no output schema, the description carries the return-format burden and does so concretely (first line with GPU/VRAM/RAM, 'N models pulled:', one line per model sorted by name, ending with LOADED now / fits in VRAM / larger than VRAM). Nothing an agent needs to call it correctly or interpret the result is missing.

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?

Zero parameters, so the baseline is 4; the description confirms 'Takes no arguments,' removing any ambiguity about whether a model name or filter can be passed. No further parameter meaning is possible.

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/resource (which models Ollama has pulled, which are loaded and at what context length, VRAM usage and fit) and adds a precise negative boundary: 'It says nothing about past calls.' An agent can distinguish it from diagnose_my_turns and last_turn_metrics purely from this text.

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?

Explicit when-to-use ('Use it before choosing a model or a context length') plus explicit routing to alternatives for the adjacent need ('for those use diagnose_my_turns (findings) or last_turn_metrics (numbers)'). Also states the re-call condition before deciding, which is an actionable usage rule.

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