create_analysis_run

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true, and the description is consistent with them rather than restating them. It adds genuinely new behavioral facts: collection happens without launching the app, hash collection is capped at 16 files, and signature validity is handled elsewhere. Missing only the resource/cost implications of openWorld access and what state the run holds afterward.

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?

Three sentences, front-loaded with the create action and its bindings, then the collection behavior, then the exclusions. Every clause carries information an agent would otherwise have to guess; nothing is repeated from the schema or annotations.

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 should say what an agent gets back — presumably a run identifier needed to drive read_analysis_run and get_run_timeline — but it never mentions the return value or how to reference the run afterward. The behavior side is well covered; the handoff side is not.

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 20% — only analysis_project_id is documented in the schema, so the description has to carry serial, device_id, package, and label. It meaningfully maps three of those (explicit ADB serial, Frida device ID, installed package), which is more than the schema offers. But label is never mentioned and no format expectations are given for the three required strings, so the coverage gap is only partly closed.

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?

Names a specific verb and resource ("Create a run") and pins down the three binding inputs: ADB serial, Frida device ID, installed package. It also states concretely what the run captures (build/ABI/page-size, up to 16 APK hashes) rather than leaving the resource abstract. It does not, however, name or contrast itself with the adjacent siblings an agent would weigh it against (start_trace, list_adb_devices, create_project).

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 negatives give real scoping: it does not launch the app, does not attach, and does not deploy frida-server, which rules out several sibling tools by implication. But there is no positive "use this when…" framing, no statement that it is the prerequisite step before start_trace/get_run_timeline, and no named alternative. Usage is inferable rather than instructed.

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