Export the debugging session

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes further with measured payload sizes (36kB vs 247kB, ~62,000 tokens) and the fact that credentials are redacted at capture. These are behavioral traits an agent could not derive from the structured fields.

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?

Front-loaded with the artifact definition, then mode semantics, then the cost rationale. Every sentence earns its place; the size/token figures and redaction note are load-bearing, not padding.

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 no output schema, the description carries the burden of describing the return value and does so thoroughly (contents of the artifact, both mode shapes, size implications). Nothing an agent needs to call this correctly is missing.

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 enum already defines both modes, so the baseline is 3. The description nonetheless adds real decision-relevant meaning beyond the schema: the measured size gap between modes and the practical implication (inline vs file), enabling a smarter mode choice.

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+resource ('export the whole session as one versioned JSON artifact') and enumerates exactly what the artifact contains: metadata, per-collector health, retention, captured events, and every diagnosis category. This distinguishes it from the sibling tools that each return one slice (get_logs, get_frames, diagnose_runtime, etc.).

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?

Explicitly routes between the two modes with concrete conditions: 'brief' for the smallest sufficient context, 'full' for bug reports, offline analysis, or a regression fixture. It even prescribes behavior ('treat full as something to write to a file rather than read inline'), which is exactly the when-to-use guidance an agent needs.

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