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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real value by naming what the record contains — read location, hash, state, and freshness — which is exactly the behavioral payload an agent needs and is absent without an output schema.

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?

One sentence, front-loaded with the verb and resource, with the id formats and return contents packed in without filler. Nothing can be trimmed without losing information.

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?

Two required params with no output schema, and the description describes the returned fields while annotations carry the safety profile, so an agent has enough to call and interpret it. It lacks only explicit sibling routing guidance to be fully self-contained.

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 50%: asset_id's accepted formats are documented, evidence_id's are not. The description compensates for that gap by specifying the EVID-/UNK- prefix forms for evidence_id, so both params now carry usable semantics.

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 gives a specific verb and resource ("Retrieve the source record behind a ... evidence id") and even enumerates the two id dialects (EVID-…, UNK-…) it accepts, which distinguishes it from generic retrieval siblings. It stops short of explicitly contrasting itself with ruthven_get_provenance or ruthven_list_evidence, so an agent still has to infer the boundary.

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?

Usage is implied by the id-based lookup framing — you call this when you hold a stable evidence id and want the backing record. There is no explicit when-to-use/when-not or named alternative (e.g. list_evidence for enumeration, get_provenance for lineage), so routing rests on inference.

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