console

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuine value beyond annotations: 'observation only; not part of a trace' clarifies the data source, and the return-shape disclosure ({messages:[{type, text}]}) plus filter behavior ('only_errors keeps warning, error and pageerror') tells the agent what to expect. No contradiction with annotations.

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?

Roughly 60 words, with the core purpose front-loaded first, followed by the observation qualifier, return shape, parameter behavior, and usage timing. Every clause earns its place; there is no filler or redundancy.

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 an output schema present and strong annotations, the description covers purpose, ordering, filter semantics, and usage timing. The only meaningful gap is explicit semantics for limit. For a simple two-parameter read-only tool, this is nearly complete.

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 0%, so the description must compensate. It does explain only_errors well — noting it keeps warning and pageerror in addition to error, which is non-obvious from the parameter name alone. However, limit is left to inference from the name and the 'newest last' ordering; the description never states that limit truncates the returned list. Partial compensation only.

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 resource ('Recent console messages and page errors') with ordering ('newest last') and a verb phrase that marks it as an observation. The 'observation only; not part of a trace' qualifier distinguishes it from tracing and network siblings, so an agent can pick it apart from network, dialogs, or page_state without opening schemas.

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?

Provides clear contextual guidance: 'Read it after an action to see what the page complained about.' This tells the agent when in a workflow to invoke it. It does not explicitly name alternative tools or state when NOT to use it, but the 'not part of a trace' note partially covers exclusions.

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