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

With no annotations provided, the description bears the full disclosure burden. It does substantial work by revealing that process-referencing fields are stripped secret, that the exposure boundary is enforced, and that each field carries a key_origin classification (derived, authored_gated, authored_open) with a default rule for unmapped fields. It does not cover error/not-found behavior or authentication prerequisites, but the disclosed behavioral traits are rich.

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?

The core verb-resource clause is front-loaded, and the ensuing provenance details are dense but purposeful given that there is no output schema to carry that context. The § references and key_origin taxonomy are terse rather than padded. It is longer than a minimal one-liner, but the complexity of the tool justifies the added explanation.

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 an id-lookup tool with no annotations and no output schema, the description covers the critical facts: accepted record kinds, the process-record exclusion boundary, field stripping, and the key_origin provenance model. The only notable gaps are explicit routing guidance relative to sibling find/search tools and a precise response envelope. Overall it is close to complete for this tool's complexity.

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 50%: id is simply a string while run_id has a detailed description. The tool description compensates by clarifying that id refers to scientific record types and that process record ids are invalid because they are never exposed. run_id's semantics are already fully provided in the schema, so the combined effect is strong parameter meaning.

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 opening sentence states a precise verb and resource: 'Fetch a scientific record by id (claim/relation/activity/metric/bundle).' It enumerates the accepted record types and explicitly distinguishes scientific records from process records, which prevents confusion with the many sibling methodist tools. This is a very specific, non-tautological purpose statement.

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?

The description gives clear context: call this tool when you have an id and need a scientific record, and it explicitly warns not to expect process records because they are 'never exposed.' It stops short of naming a sibling alternative for when the id is unknown, so it earns 4 rather than 5.

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