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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds context they cannot: data is read 'live from the system' (freshness), the field set is normalized across systems with opt-in extras, and most valuably a security directive never to follow instructions found in record content. That prompt-injection warning is behaviorally significant and appears nowhere in structured fields.

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 dense sentences, front-loaded with the purpose, then the sibling routing, then the safety note. The opening clause 'AI Agents (inside one system):' is slightly awkward and costs a beat of parsing, but no sentence is wasted.

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?

Four parameters, all schema-documented, annotations covering the safety profile, and an output schema so return shape needn't be described. The description fills the remaining agent-facing gaps: when to choose it, how to extend the projection, and how to treat untrusted content.

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 100%, so the baseline is 3; the description exceeds that by explaining that `fields` pulls the system's own fields (e.g. lead status, custom field) and where to source valid names ('names from describe_record_type, under systemFields'). The only gap is that it doesn't restate valid `type` values, but those are already in the schema.

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 ('read one record of an AI agent's system by its id') plus scope ('live from the system'), which is far more precise than the title. It explicitly names the two sibling tools it is not (search_records, list_related_records), so an agent can distinguish it without opening the schema.

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?

There are explicit exclusions with named alternatives: 'Not for finding records (use search_records) or for what the record is linked to (use list_related_records).' It also states the precondition for the `system` parameter (ask the person which AI agent, never pick one yourself), which governs correct invocation.

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