fahali_get_evidence

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

Annotations already cover read-only, idempotent, non-destructive, so the safety profile is settled. The description adds substantive context beyond that: the snapshot is hashed at decision time and hash verification is returned, and 'explicit retention gaps' signals that missing data is a normal, disclosed outcome rather than an error. It does not discuss pagination or how large the retained event sets can get.

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 sentences, front-loaded with identity and followed by the contents and the one actionable usage rule. The middle sentence is a dense enumeration but each item earns its place; nothing is padded.

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?

An output schema exists, so enumerating return fields is partly redundant, but naming hash verification and retention gaps tells the agent what to look for in the response. The main gap is routing: with this many adjacent verdict/evidence siblings, an explicit alternative would have closed the definition.

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 a moderate 63%, and the description reinforces the detail enum tradeoff rather than adding new syntax. Five parameters (limit, offset, since, symbols, evidence_ids, include_withheld) carry no guidance in the description, though symbols/include_withheld are documented in the schema itself.

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 ('Fetch the ... evidence behind one immutable portfolio verdict') with scope qualifiers: compact, content-addressed, single verdict. This clearly separates it from sibling tools like fahali_get_verdict_by_id (the verdict itself) and fahali_get_verdict_history (the list).

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?

It gives a decision rule for the detail parameter ('summary for routine audit, full only when raw source metadata is required'), which is genuinely useful. But it never says when to reach for this tool instead of fahali_get_portfolio_decision, fahali_get_verdict_by_id, or fahali_get_bundle, all of which sit close to the same data.

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