run_experiment

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

With no annotations, the description carries the full burden. It does disclose meaningful behavior: a run start time, software version, model/provider metadata, and an optional seed are recorded, and results are populated later by other tools, implying persistence and a multi-step lifecycle. It omits error behavior for an invalid experiment_id, whether repeated calls create duplicate runs, and any permission requirements.

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?

Three short sentences with the core action front-loaded and the workflow note placed last where it belongs. No filler, though the middle sentence is a slightly loose inventory of recorded metadata.

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?

An output schema exists, so return values need not be described, and the lifecycle guidance covers the key sequencing. However, with zero annotation coverage and an unexplained free-form bounded_inputs parameter, an agent still lacks enough to call this confidently in edge cases.

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 0% for three parameters, so the description must compensate and largely does not. It mentions the optional random seed, but experiment_id is only indirectly implied by the experiment framing, and bounded_inputs — an arbitrary object — is never explained at all, leaving the most ambiguous parameter undocumented.

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: "Create a new run of a bounded scientific experiment." That clearly separates it from create_experiment (defines the experiment) and complete_experiment (closes a run), though it never names those siblings explicitly, so differentiation is inferred rather than stated.

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?

It gives a usable lifecycle instruction: populate results via approved MCP tools, then call complete_experiment, which points to the correct follow-up tool. It does not say what must exist beforehand (create_experiment, presumably) or when to prefer list_experiment_runs instead of starting a new run, so the when-not side is absent.

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