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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful domain context — that hermes is the agent and agentd is bootkey's daemon — but says nothing about truncation, ordering, or what an empty journal means, which are the real behavioral questions for a tail-style log read.

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?

A single short sentence with no filler, and the unit meanings are front-loaded where they matter. The fragmentary noun-phrase construction is slightly awkward as a standalone definition but costs nothing in practice.

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 only three simple parameters, no output schema, and annotations covering safety, the definition is close to sufficient for calling the tool correctly. It still leaves the return shape and truncation behavior unstated, which for a log-tailing tool is the one piece of context an agent would most want.

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 only 33%, so the description has to compensate, and it does explain the two enum values of 'unit' in domain terms. It adds nothing about 'lines' (beyond the schema's default 200 / max 500) and nothing beyond the schema's own note on agent_id, leaving the non-required parameters thin.

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 the specific resource retrieved — the last lines of an agent's system journal — and disambiguates the two units (hermes is the agent, agentd is bootkey's daemon on its box). It is a noun phrase rather than a verb+resource statement and does not distinguish this from the sibling read_agent_files, but the resource is clear enough that an agent knows what it gets back.

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 no when-to-use guidance, no prerequisites, and no mention of alternatives such as read_agent_files, which sounds closely related. The agent must infer that this is a diagnostics/tailing tool from the word 'journal' alone.

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