evidence

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

With no annotations, the description carries the full burden. It usefully discloses the mutation semantics: passing `method` creates a new experiment node, passing `node` registers something already captured. Beyond that it says nothing about permissions, reversibility, failure if the hypothesis is absent, or what is returned.

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 core action is front-loaded in the first sentence, and the parameter routing follows logically. The parenthetical `cargo test` aside is slightly gratuitous but the whole thing stays to three tight sentences.

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 4-param mutation tool with no annotations and no output schema, the description covers purpose and the method/node choice but leaves gaps: the unexplained `initiative` param, the return/error behavior, and any prerequisites around the hypothesis are unaddressed.

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 75%, so the schema already documents most parameters, including the 'Give this OR `node`' mutual exclusivity. The description adds the past-tense framing for `method`, but largely restates schema content and does not explain the undocumented `initiative` parameter. Baseline 3 fits.

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 names a specific verb+resource ('record... evidence') and its scope ('attach it to a hypothesis'), which sets it apart from generic linking tools like attach/link. It further clarifies what it is not (scheduling, `cargo test`). It doesn't explicitly contrast against close siblings such as cite/claim/episode, so it stops short of a 5.

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 real usage context — past tense, documents a check that already ran, does not schedule — which implies when to reach for it. However it never names an alternative sibling (cite, claim, episode, attach) or states when-not to use this versus those, so the when/when-not guidance is incomplete.

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