snapshot

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety burden is lifted. The description adds that it is 'one-shot' and what each scope captures, but says nothing about session targeting, cost, or what the capture returns. Moderate additive context.

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?

Purpose is front-loaded in four words and the rest is dense with no filler. The telegraphic 'scope=full([...]) | rtos' notation is compact but slightly cryptic on first read.

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 7-parameter diagnostic tool with no output schema, the definition explains the scopes but leaves the return shape, the session parameter, and how the capture interacts with active sessions unexplained. Usable, but not fully self-contained.

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 100%, so the baseline is 3. The parenthetical correctly associates include_project/include_rtos/include_logs/log_limit/project_root with the full scope, which adds a little ordering meaning, but it never mentions the session parameter and gives no format or default details.

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 action (one-shot diagnostic snapshot) and enumerates the two scopes with what each collects (registers+stack+faults vs task/queue state). It does not distinguish itself from near-siblings like capture_state or session_diagnostics, which is the only thing keeping it off a 5.

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 scope semantics ('full bundles registers+stack+faults; rtos captures task/queue state') imply which mode to pick, but there is no explicit when-to-use/when-not guidance and no mention of the alternative snapshot-style siblings. Adequate implied usage only.

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