register_evidence

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

With no annotations, the description carries the full burden and does well: it discloses that the file is hashed and type-detected, that it is never copied or modified (a strong non-destructive guarantee), that an allowed_roots constraint applies, and the shape of the returned id. It omits error behavior on invalid paths or duplicates, and whether registration mutates the active case.

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 tight lines: the effect and its guarantees first, then the constraint, then the return value, then a single example. Every sentence contributes new information and nothing is repeated from the schema.

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 3-parameter entry-point tool with no annotations and no output schema, the description supplies the essential context: what is done to the file, the path restriction, and the id returned for downstream tools. The gap left is the undocumented `label` parameter and failure modes, which is a modest but real omission.

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. It documents `path` reasonably (allowed_roots constraint plus an example format) and the file-type vocabulary ('pcap/pcapng or rules') hints at valid `type` values, but it never explains the optional `type` override versus the automatic type detection, and `label` is not mentioned at all.

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 (register) and specific resource types (pcap/pcapng or rules file) scoped to the active case, and states what the operation does mechanically: hashed, type-detected, never copied or modified. The closing sentence that it returns the evidence id used by other tools positions it unambiguously against siblings like write_rules_file and the analysis tools (run_pcap, validate_rules) that consume the id.

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?

Provides one hard precondition ('path must be under allowed_roots') and a concrete example call, which is real guidance for invoking it correctly. However, it never states when to choose this over alternatives, whether re-registering the same path is allowed, or what to do when the path is outside allowed_roots; usage is implied rather than spelled out.

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