tail_site_logs

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

Annotations already mark the operation as read-only, and the description adds useful behavioral facts beyond that: the 1000-line cap and the best-effort substring filtering limitation with a pointer to the note in the result. It does not need to restate read safety.

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 compact sentences front-load the core purpose and cap, then deliver the key caveat about domain filtering. No filler or redundant clauses.

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 three-parameter, read-only log-tail tool with an output schema present, the description covers the essential behavioral constraints (line cap, domain caveat, result note). Additional details would be redundant with the schema and output schema.

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 100% and the prose largely mirrors the schema (e.g., 'capped at 1000' appears in both). The description adds no new parameter-level detail beyond what the schema already provides, so the baseline 3 is appropriate.

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 states a specific action ('Tail') on a specific resource ('nginx's access or error log') with an important bound ('capped at 1000 lines'). This clearly distinguishes it from all siblings, none of which read logs.

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 are no sibling log-reading tools to contrast with, but the description gives clear context for invoking the tool and explicitly warns that the domain parameter is not a true per-vhost filter. It stops short of an explicit when-to-use/when-not-to-use statement.

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