ESPHome build activity

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description only needs to add context, and it does: the view is session-scoped ("started in this session"), includes recently finished as well as running jobs, and supports incremental polling via the seq/since handshake. The one gap is that it doesn't say how long finished jobs or their lines are retained, which matters for a session-scoped buffer.

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 sentences, front-loaded with what the tool returns, then the polling contract, then the when-to-use note. Every sentence carries information; the only minor cost is that the parenthetical command list slightly lengthens the first sentence.

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, the description must convey the return shape, and it does at a high level (jobs plus their newest output lines, plus a seq cursor). It is enough to call the tool correctly, though the exact envelope (per-job fields, whether finished jobs eventually drop out) is not spelled out.

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%, so the baseline is 3, but the description adds real meaning by tying the two fields together: "Pass back the returned 'seq' as 'since' to get only lines produced after it," explaining the cross-reference the schema alone does not make obvious. The instance_id parameter's refusal behavior is left entirely to the schema, which is acceptable at full coverage.

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 resource (the ESPHome build commands validate/compile/upload/logs started in this session) and states precisely what is returned: each running or recently finished job with its newest output lines. It also explicitly separates itself from the build tools themselves, which return full output only on completion, so an agent can distinguish it from esphome_validate/esphome_compile/esphome_upload/esphome_logs without opening any schema.

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?

"For watching a long build while it runs; the build tools themselves return the full output when they finish" gives a clear condition for choosing this tool over the one-shot build commands. It stops short of an explicit when-not (e.g. don't poll after the job has finished or after a session restart), but the alternative is named and the context is unambiguous.

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