logs_errors

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

Beyond the readOnlyHint annotation, the description discloses two real behavioral facts: only the single most recent file is examined (not a history), and no editor connection is required. It does not say what happens on missing Logs directory or zero matches, but the annotations already cover the safety profile.

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 sentence with no filler. The behavior-defining constraint (most recent file) is stated up front, and the qualifier ('without running the editor') is appended where it belongs.

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?

A zero-parameter tool with an output schema and readOnlyHint coverage: the description supplies everything an agent needs to decide to call it — the source file selection rule and the line filter. Return shape is handled by the 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?

There are zero parameters, so no parameter semantics are required; the schema is trivially complete. The description adds nothing to explain, which is appropriate here rather than a deficiency.

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?

States a specific verb (extracts), the exact selection criteria ([Error]/[Warning] tagged lines), and the exact source (the project's most recent Logs/*.txt). An agent can distinguish this from the sibling logs_tail purely from the description, since 'most recent file only' versus tailing are clearly different behaviors.

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 phrase 'without running the editor' implies the usage context (offline/no-host scenario), but the description never states when to prefer this over logs_tail or what to do if you need older log files. Usage is inferable rather than prescribed.

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