complete_experiment

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

With no annotations at all, the description carries the full burden. It does disclose that this is a terminal state transition that records a completion timestamp plus result/error payload. It does not say whether the call is idempotent, what happens if the run is already complete, whether the error path aborts or supplements the result, or what permissions are required — meaningful gaps for a mutation tool with zero annotation coverage.

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, front-loaded with the action, then the recorded fields, then the precondition — each sentence carries distinct information. Slight redundancy between the opening phrase and 'Records ... result summary' but nothing wasted.

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 no explanation. However, for a state-mutating lifecycle tool with no annotations, the description should address re-invocation behavior and failure modes. As written, an agent knows what to send but not what happens on a run that is already finished or invalid.

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 description coverage is 0%, so the description must compensate and it only partially does: it names all three concepts (run id, result summary, error message) but adds no format or exclusivity semantics — e.g. whether result_summary and error_message are mutually exclusive, or what keys result_summary expects. It maps parameters to meaning without enriching them.

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 and resource ('Mark an experiment run as complete') and names the payload semantics ('with results or error'), which separates it from create_experiment, run_experiment, and get_experiment_result. It doesn't explicitly name those siblings, but the lifecycle role is 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?

Gives one real prerequisite: the agent 'should have gathered results from approved MCP tools before calling this.' That is a usable when-to-use cue. It stops short of routing guidance — it never says to call run_experiment first or to use get_experiment_result instead for reading state, and gives no when-not-to-use condition.

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