read_analysis_run

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely new behavioral information: the call works purely against retained artifacts and never touches a device, and it enumerates the payload it returns — valuable since no output schema exists.

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?

A single dense sentence with the resource list front-loaded and the key qualifier ('without contacting a device') at the end. No filler, though the enumerated payload list is slightly list-like for one sentence.

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, enumerating the returned artifacts is a real contribution, but the definition omits how a run_id is obtained and what the tool returns when a run has no registered traces or storage acquisitions. Adequate but with clear gaps for an agent invoking it cold.

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 only 50%: run_id has constraints but no prose, and analysis_project_id is documented in the schema. The description says nothing about either parameter — not what a run_id looks like, not where to obtain one (presumably create_analysis_run), and not the retention side effect of analysis_project_id.

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 ('Read') and enumerates the concrete resources returned: run manifest, target identity, registered trace files, storage acquisitions. The qualifier 'retained' plus 'without contacting a device' separates it from live-device siblings like start_trace or inspect_adb_device, though it never names create_analysis_run or get_run_timeline directly.

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?

Usage is only implied: 'retained' and 'without contacting a device' suggest this is the offline path for inspecting a previously captured run. There is no explicit statement of when to prefer this over get_run_timeline or inspect_trace, and no prerequisites or exclusions are given.

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