gradebook

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals a 'shows' behavior in the second sentence, but the first sentence 'Grade items' hints at a mutating action, and there is no explicit statement that this tool does not write grades. Safety-critical behavior, such as whether it is strictly read-only and what happens with insufficient permissions, is left ambiguous.

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 description is two sentences with no filler, stating scope first and then the result. It is well-structured, though resolving the 'Grade items' ambiguity with a word like 'View' would have made it more precise without adding length.

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 low-complexity tool with only two documented parameters, the description covers the main invocation context and what the result conveys. However, with no output schema and no annotations, it would be more complete if it explicitly stated that this is a read-only lookup and described how empty marks are represented in the result.

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 100%, so the schema already documents courseid and userid including the '0 for everyone visible' default. The description mostly restates that scope and adds little beyond what the schema provides, so the baseline of 3 is appropriate.

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 identifies the resource (course grade items) and the action is reasonably clear: it shows which items have marks and which are still empty, for one student or everyone visible. It is not a tautology, but the verb 'Grade' in 'Grade items' can briefly be read as writing marks rather than viewing them, and it does not explicitly differentiate from grade_submission.

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 useful scoping context: a courseid is required and userid can target one student or 0 for everyone visible. However, it never explicitly says when to use this tool versus siblings like grade_submission or missing, so the usage is only implied rather than clearly delineated.

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