Tower agents

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

With readOnlyHint=true already declaring the safe-read profile, the description adds genuine non-annotation context: that returned evidence is untrusted, that record IDs should be cited, and that uncertainty must be preserved. It still omits return shape, pagination, and how filtering behaves, so it is useful but thin beyond the trust-model warning.

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 with no filler, but the front-loaded sentence is the vaguest one, so the piece fails to lead with the tool's actual purpose. Efficient in length, weak in prioritization of information.

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 tool with four undocumented optional filters, no output schema, and no enums, the description should carry the burden of explaining parameter meaning and result shape. It covers only the trust/approval model, leaving the operation and its filtering semantics unexplained.

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% and none of the four parameters (status, capability, environment, missing_capability) are mentioned in the description. With the schema providing no semantics and the description offering none either, the agent has no idea what these filters mean or how they combine.

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 is a noun phrase that mostly restates the tool title ('Tower agents'), qualified as 'Local authenticated'. It never states an action verb, so an agent cannot tell whether this lists, filters, or inspects agents, nor how it differs from tower.status or tower.posture.

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?

'Human approval uses Tower HTTP/CLI separately' implies this tool is not the approval path, which is a faint boundary signal. Otherwise there is no statement of when to call this versus tower.evidence, tower.investigate, or other siblings, and no prerequisites beyond the word 'authenticated'.

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