record_read

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

With no annotations the description carries the full burden, and it does unusually well: it enumerates exactly which fields are masked per surface (owner full email, analytic domain-only, phone always partial, gov/payment/health null) and notes the call is 'Receipted', so the agent knows an audit trail is produced. It omits error behavior (missing record, unauthorized surface) and whether the read is side-effect free beyond the receipt.

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?

Masking rules are front-loaded in a single dense parenthetical and 'Receipted.' closes with a meaningful behavioral footnote. Every clause earns its place, though the parenthetical is heavy enough that a structured list would scan faster.

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 a two-parameter read with no annotations and no output schema, the masking and receipt notes cover the most important surprise (redacted fields), but the description says nothing about the shape of the returned record or about failure modes. Adequate to call correctly, not complete enough to predict the response.

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 0%, so the description must compensate, and it partially does by defining what 'surface' means via the owner/analytic examples and their masking consequences. It never states the allowed surface values as an enumeration nor confirms that record_id is the canonical graph record identifier, so one parameter remains essentially undocumented.

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?

A specific verb ('Read') and resource ('one graph record') with a stated scope of applying egress masking, which separates it from record_search (multi-record lookup) and record_ingest. It stops short of naming a sibling to route away from, so it is clear but not sibling-differentiating in the strongest sense.

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 phrase 'Read one graph record' implies retrieval by ID, and the exposure of a 'surface' parameter signals that callers choose an egress context, but there is no explicit when-to-use guidance, no statement of when to prefer record_search, and no prerequisites. Usage is inferable rather than stated.

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