get_diagnostic_snapshot

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

With no annotations provided, the description carries the full behavioral disclosure burden and does it thoroughly. It explicitly discloses read-only behavior ('only reads cache'), process-global cache persistence ('survives across cases'), and the carried_over edge case. This goes well beyond what the tool name alone reveals.

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?

The five sentences are dense and purposeful: what it is, its non-executing behavior, what it returns, how to use it at session start, and the fallback when no target is given. The critical constraints are front-loaded, and no sentence feels redundant.

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 tool with no output schema, the description meaningfully describes return content ('availability status, compact summaries, and suggested calls for missing steps') and even names the carried_over signal. It also covers both usage paths — passing a target case and passing no target — so an agent has enough context to call and interpret the tool correctly.

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?

The input schema already provides rich, detailed descriptions for both optional parameters, covering case validation and cold-start degradation, so the 100% coverage baseline applies. The description adds only a small 'verif_root and/or case_dir' combination hint and the no-target fallback, but largely restates schema semantics rather than offering materially new parameter meaning.

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?

The description opens with a concrete role ('Cold-start accelerator') and a concrete action ('aggregates cached tool results into a single summary view'). It further distinguishes itself from the sibling debugging tools by stating 'It never triggers sub-steps and only reads cache.' This is a clear, specific definition rather than a tautology.

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?

The description gives an explicit usage context: 'at the start of a new session pass your target case (verif_root and/or case_dir)'. It also names a relevant alternative when no target is passed: 'confirm it or re-run get_sim_paths.' It does not enumerate broader when-not-to-use scenarios, so it falls just short of a 5.

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