Download Diagnostic Archive

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuinely new behavior: archives are time-limited and can be evicted, content is base64-encoded, and integrity should be checked against the exported SHA256. It leaves out what happens at end-of-archive or after eviction, and why idempotentHint=false despite a byte-addressable read.

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?

Two short sentences, zero filler, with the core read semantics front-loaded and the operational caveats (expiry, SHA256 verification) trailing in a single compact clause.

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, return-value detail is not needed, and the description covers the essentials for a chunked read. The remaining gap is how an agent knows it has reached the end of the archive or should retry after eviction.

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 only 33% (only max_bytes has a schema description), so the description must compensate. It does: it defines offset as an archive byte offset explicitly not a session cursor, ties diagnostic_id to the archive, and restates the 65536 upper bound that governs max_bytes.

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+unit: read ZIP bytes of a diagnostic archive by diagnostic_id and byte offset, returned as base64. That is precise enough to distinguish it from terminal_export_diagnostics (creation) and from cursor-based reads, though it never names those siblings explicitly.

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 real usage context: call before the archive expires or is evicted, and verify the exported SHA256 afterward. The clause 'This offset is not a Session cursor' pre-empts the most likely misuse (confusing it with terminal_read/terminal_wait cursor semantics). It does not say whether terminal_export_diagnostics must run first.

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