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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real behavior context by enumerating what the record contains (grader's own record match, tap verification count, provenance chain events) and by instructing the agent to 'report what this proves AND what it does not'. It omits error/not-found behavior for an unknown item_id.

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?

Front-loaded with the subject, then usage examples, then a short directive. The field enumeration is long but each item is informative; nothing is gratuitous filler.

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 single-parameter read tool with no output schema, the description does well: it sketches the returned record and its provenance chain without needing to define a return shape. The one real gap is that item_id and the failure mode for a bad ID are left unaddressed.

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 description coverage is 0% and the single parameter item_id is unexplained in both the schema and the description; the agent gets no hint about format, origin, or how it relates to other identifiers in the domain. With low coverage the description was expected to compensate and does not.

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 is framed as a payload definition ('A graded item as Aeroz holds it: grader, cert, grade...') rather than a stated action; it never says plainly that this fetches a single graded item by ID. The usage examples imply a lookup, but the sibling list_graded_items is never distinguished from this tool, so the agent must infer the single-item scope.

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?

Three concrete trigger questions ('is this slab the one that was sealed', 'where has it been', 'has anyone tried to pass off a copy') give clear context for when to reach for this tool. It stops short of naming alternatives or exclusions, e.g. when to use list_graded_items or trace_unit instead.

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