get_logs

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

No annotations are present, so the description carries disclosure. It reveals sanitization, size-capping, per-service pod limit, and the previous-container behavior, which go beyond the schema. It does not describe output format or pagination, but for a read-only logs tool the disclosed traits are substantive.

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, each adding a distinct fact and no filler. Essential scope and edge-case usage are front-loaded.

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?

Given eight parameters, no annotations, and no output schema, the description is adequate but incomplete: it lacks explicit namespace guidance, output shape, and alternative-tool routing. The schema fills some gaps (namespace required, tail max), but the description alone would not fully support a confident 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 coverage is about 63%, and the description adds semantics for grep ('substring or /regex/i') and previous ('crashed container'). It does not clarify container, namespace, or tail defaults beyond the schema, leaving some burden unmet.

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 the resource (container logs) and scope (a service up to 10 pods or a pod), with important qualifiers (sanitized, size-capped). It does not use an explicit verb and does not name sibling tools, but the resource and scope are specific enough to separate it from access-log or error-summary tools.

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 actionable conditions: use previous=true for crashed-container logs and grep accepts a substring or /regex/i. It does not explicitly discuss when to prefer this over siblings like summarize_access_log or summarize_log_errors, so the guidance is context rather than exclusions.

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