Tower capability_contract

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

readOnlyHint=true already establishes the safety profile, yet the description adds genuinely new behavior: a version gate, the epistemic stance that returned evidence is untrusted and must be cited by record ID with uncertainty preserved, and the boundary that approval happens out-of-band. What it does not cover is failure behavior when the version gate is unmet or when no descriptor is present.

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 tight sentences: what is read, then the version precondition, then the evidence-handling and approval-boundary rules. No filler, and the resource identity is front-loaded. The phrasing is dense with internal jargon ('candidate descriptor', 'reported status semantics') that may cost a first-time reader.

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?

With no output schema and no parameters, the description must carry the return shape, and it only gestures at it by enumerating 'descriptor, schemas and reported status semantics' without saying what those records look like or how they are keyed for citation. The evidence-citation instruction is useful but presupposes record IDs the description never explains are returned.

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?

The tool takes zero parameters with additionalProperties=false, so there is nothing for the description to disambiguate. Baseline for a parameterless tool applies; the description correctly implies the call is scoped entirely by the Tower-local environment rather than by any argument.

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 uses a specific verb ('Read') tied to a named resource: the Tower-local tower.capabilities.v1 candidate descriptor, schemas and reported status semantics. That is far more concrete than a restatement of the name. It stops short of distinguishing itself from close siblings such as tower.versions, tower.status, or core.compatibility, which an agent may see as overlapping.

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?

There is an explicit prerequisite ('Requires Tower 0.10+') and an implicit exclusion ('Human approval uses Tower HTTP/CLI separately'), which tells the agent this tool does not perform approvals. However, it never says when to choose this over the many adjacent tower.* and core.* read tools, so selection remains partly inferred.

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