aa_inventory

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the result goes into a *new* JSON file, which is consistent with non-destructive behavior, but it omits whether an existing 'out' file is overwritten, how large a tree it will walk, and what a 'fingerprint' contains.

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 front-loaded sentence with no filler and no repetition of the schema or annotations. It is efficient, though the terseness tips into under-specification rather than being maximally informative.

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 filesystem-writing tool with three parameters, partial schema coverage, and no output schema, the description leaves too much implied: fingerprint algorithm/fields, recursion behavior, overwrite semantics for 'out', and the shape of the produced JSON. An agent would have to guess before invoking it.

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 only 33%: 'exclude' is documented in the schema, while 'target' and 'out' are bare strings. The description only loosely maps them ('local files' for target, 'new JSON file' for out) and leaves open whether target is a directory, a single file, or a glob.

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 and resource: fingerprint local files into a new JSON file. An agent can tell this apart from the sibling aa_* workflow tools (start/status/upsert/render), none of which do file inventory. The verb 'fingerprint' is slightly jargon-y (hash? metadata?) but the core action is clear.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives or where this fits in the aa_* pipeline. 'Selected' hints that some scoping applies but never explains how selection works or when an agent should call this instead of plainly reading files.

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