find_blobs

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

No annotations are provided, so the description carries the full behavioral burden. It does not say whether the tool only reads the input, whether it writes carved blobs to disk, what outdir does, or what limits or side effects exist. The only behavioral clue is the verb carve, which is insufficient for a mutation-capable tool with an outdir parameter.

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 description is a single front-loaded sentence with no wasted words. Every part earns its place, including the parenthetical kind examples. It is terse but not padded, though it is arguably undersized for a tool with four parameters and no 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?

The tool has four parameters, no annotations, no output schema, and 0% schema description coverage. The description explains what the tool does and some kind values, but omits critical context: what path points to, what limit controls, whether outdir writes files, and what the tool returns. This is not enough for an agent to call the tool correctly without guessing.

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%, so the description must compensate for all four parameters. It partially compensates by listing kind values (zip, pe, gzip), which is useful beyond the schema. However, path, limit, and outdir remain completely unexplained, leaving most parameter semantics undocumented.

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 states a specific verb and resource: carve embedded archives or PEs. It names the signature-based method and gives concrete kind values (zip, pe, gzip), making the purpose clear. It does not differentiate against sibling tools like yara_scan or bin_info, so it stops short of 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 description implies usage by stating what it carves, but it gives no explicit when-to-use guidance, no prerequisites, and no alternatives. With many sibling scanning tools available, the agent gets no help choosing between find_blobs and tools like yara_scan or strings_scan.

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