splithub_plan

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

With no annotations, the description carries the burden and does so: it discloses that sizing is performed by SplitHub Cloud, that no account is needed, and that it fails with UNREACHABLE when offline. It also frames the sequential verdict context. Missing only rate-limit/timeout behavior for the remote call.

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 precondition 'Before creating an experiment', which is good. However the middle sentence is a run-on with stacked parentheticals ('(and in all)', '(no account needed; fails with UNREACHABLE offline)'), making it harder to parse than necessary.

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-parameter tool with no annotations and no output schema, the description tells the agent what comes back (visitors per variant and total, optional days-left) and what failure looks like. Adequate, though it doesn't state the return shape explicitly enough to rely on without an output schema.

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 100% with unit examples already in the schema ('0.1 for +10%', '0.05'), so parameter meaning is largely carried by structured data. The description adds the aggregate-vs-per-variant distinction and the 'days at current traffic' effect of `experiment`, but not much beyond the schema baseline.

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 function: sizing visitors per variant (and total) to detect a relative lift `mde` against a `baseline` rate, plus optional days-left for an experiment id. That verb+resource is distinguishable from creation/status siblings, though the phrasing 'visitors per variant (and in all) to detect a relative lift' is dense enough to require a re-read.

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?

'Before creating an experiment' gives an explicit temporal condition for use, and 'if it takes months, suggest a bigger change or a busier page' guides interpretation. It does not name a sibling alternative (e.g. splithub_experiment_create) by name, so routing is implied rather than explicit.

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