review_manifest

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral signal beyond that: the tool returns supporting evidence rather than a security conclusion, which shapes how an agent should interpret and present results. It says nothing about pagination, truncation, or what happens when the decoded manifest is missing.

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?

It is a single short sentence with no filler, so nothing is wasted, but the brevity comes at the cost of specification rather than being earned by density. The most informative part ("not security verdict") is trailing and easy to skim past.

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, no annotations gap, 0% parameter coverage, and a required job_id that is never defined, the description leaves an agent unable to call the tool confidently. It should at minimum state what job_id identifies, what the path default means, and what form the returned evidence takes.

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 0% across two parameters, so the description must compensate and does not. "Decoded manifest" loosely hints that path refers to a decoded AndroidManifest.xml (default apktool/AndroidManifest.xml), but job_id — the required parameter — is never explained, nor is the relationship between job_id and path.

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?

"Review decoded manifest" gives a verb and a resource, but "review" is ambiguous about what is actually produced (extracted fields? raw XML? flagged entries?). The clause "not security verdict" does differentiate it from analyze_apk-style siblings, but only by negation, so an agent still cannot fully predict the output.

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 phrase "with evidence, not security verdict" implies a boundary (don't use this for a security assessment), but no sibling is named and no positive condition for choosing this over inspect_apk, analyze_apk, or read_artifact is given. Prerequisites such as needing a previously decoded APK job are left to inference.

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