console_read

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds value beyond that by disclosing the bounded-result behavior, cursor continuation semantics, and the maximum blocking duration — traits an agent would otherwise not know.

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 short sentences, zero filler, front-loaded with the purpose before the parameter guidance. Every sentence carries distinct information.

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 read-only, no-required-parameter tool with no output schema, this covers purpose, polling behavior, and pagination adequately. The main residual gap is not stating that the returned cursor must be read from the response body before the next call.

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 only 33% (just table_id), so the description must compensate — and it does, explaining after_cursor's continuation role and that wait_ms blocks up to 20 seconds, which resolves the schema's unit-ambiguous maximum of 20000. It stops short of stating what value the response returns as the next cursor.

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 and resource ("Read bounded console logs") and narrows scope by naming the content type ("compilation/runtime errors"), which separates it from generic event streams. It does not, however, explicitly name or contrast with a sibling such as events_read, so the differentiation is inferred rather than stated.

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?

Gives concrete operational guidance: pass after_cursor from the previous call for pagination, and use wait_ms to poll for new logs with a stated 20-second ceiling. There are no explicit exclusions or named alternatives, but the polling/pagination context is clear enough to act on.

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