Open an evidence case

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 evidence is SHA-256 hashed at collection time, persisted to ~/.scamcheck with mode 0700, and is local-only. It omits whether re-opening/duplicate cases are possible, what identifier or path is returned, and any failure modes (disk, permissions).

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?

Two sentences, zero filler: the first covers what happens and where data lands, the second covers when to use it and what the artifact is good for. Storage and hashing are front-loaded before the usage guidance.

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?

A six-parameter mutation tool with no annotations and no output schema — the description supplies storage location, permissions, integrity mechanism (hashing), and downstream export paths, which is most of what an agent needs. The notable remaining gap is what the call returns (case ID or path) so the agent can reference the case later.

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 100%, so all six parameters are already documented; baseline is 3. The description adds only marginal meaning by indicating evidence_text is optional and gets hashed, and says nothing about currency, loss_amount, scam_type, or notes.

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 — 'Open a local evidence case' — plus the optional attachment of analysed text, which is clearly distinct from the read-only checking siblings (check_number, check_message, check_url). It doesn't explicitly name a sibling as the alternative path, so the differentiation is inferred rather than stated.

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?

'Use this when a user wants to report a scam or preserve proof' gives an explicit trigger condition, and the follow-on paths (--case-export, --report) tell the agent what the case is for downstream. No when-not guidance or comparison to the check_* tools, but the usage context is unambiguous.

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