register_host

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

The annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by spelling out upsert semantics: 'omitted fields keep their previous values,' which tells the agent that a partial payload will not wipe existing host config. It does not address permissions, conflicts on re-registering an existing host_id, or error behavior, so it is not a 5.

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?

Two short sentences, zero filler, and the core purpose is front-loaded before the upsert caveat. Every clause earns its place.

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 7-parameter upsert with an output schema and 86% schema coverage, the description supplies the one piece of semantics the schema cannot express: partial-update retention. An agent has enough to call it correctly. It could go further on re-registration conflicts or required prerequisites, but nothing essential is missing.

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 86%, so the schema already documents host_id format, ssh_target form, shell enum, ssh_key path, hostname, and os. The description adds only the cross-parameter rule that omitted fields retain prior values, which is useful but does not enrich individual parameters. Baseline 3 is appropriate when the schema carries the parameter burden.

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 pair and resource: 'Register (or update) a test/build host.' That distinguishes it from read-side siblings like list_hosts and get_host and from lifecycle siblings like claim_host and release_host, since it is clearly the create/upsert path. It stops short of naming those siblings explicitly, which keeps it at 4 rather than 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?

The parenthetical '(or update)' implies the tool is the entry point for getting a host into the registry, so an agent can infer it should call this before claim_host or probe_host. However, no explicit when/when-not guidance is given, and no sibling is named as an alternative. Usage is implied rather than stated.

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