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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered; the description adds genuinely non-redundant behavior: initial status is Idea, the returned ID works across hypotize_experiment_* / vote / comment, role-based failure semantics, and framework defaulting when omitted. The notable omission is the required idempotency_key, whose retry/dedup behavior is never explained anywhere.

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 core action and scope, then progressively adds the import alternative, downstream ID reuse, optional fields, and permissions. Dense but nearly every clause adds decision-relevant information; the parenthetical tool list is the only slightly padded portion.

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?

Strong on identity, alternatives, permissions, and status, but with no output schema and 18 undocumented parameters the agent still cannot tell what most fields mean, what the response body contains beyond an ID, or how idempotency_key affects retries. Adequate for the happy path, incomplete for a create tool of this surface area.

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% across 18 parameters, so the description must carry the semantic load, and it only names six optional definition fields and the framework default. Required parameters like idempotency_key, funnel (an enum), and short_idea get no explanation, and variants, tags, target_segment, and success_metric are unmentioned entirely.

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 ("Create one experiment") and immediately resolves the domain ambiguity that an Idea *is* an experiment, not a separate object. It names the sibling it is not (hypotize_experiments_import) and lists the downstream tools the returned ID unlocks, so an agent can place the tool precisely in the family.

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 an explicit alternative with the condition that selects it: use hypotize_experiments_import for a batch or for experiments already past Idea. It also states the permission gate (editor/owner required, contributor/viewer get INSUFFICIENT_ROLE with required_roles), which tells the agent when the call will fail rather than leaving it to discovery.

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