get_grades

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that it returns a list of grades, without mentioning side effects, authentication requirements, or data scope. It does not state whether it requires a pre-existing session or if it affects any state. This is a significant gap for a tool that likely requires login but does not say so.

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 extremely concise: one sentence with an optional filter clause and a brief note on the return content. There is no filler or redundant wording. It achieves clarity with minimal length, which is ideal for efficient agent parsing.

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?

While the description covers the basic purpose and optional filters, it lacks essential context for a robust tool: no output schema, no mention of error conditions, no authentication requirements (though sibling login tools suggest auth may be needed), and no note on whether the data is scoped to a particular user or session. For a tool that likely requires login and returns sensitive data, this is incomplete.

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?

The description adds valuable information for two of the three parameters (year and term), including acceptable term values ('FIRST' or 'SECOND'), which is not in the schema. However, the third parameter, 'subdomain', is entirely omitted from the description, leaving it undocumented. Since schema coverage is 0% and there is no description field, the tool relies on the description text, which is incomplete.

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 clearly states the verb 'Get' and the resource 'grades', and mentions it returns a list with subject, teacher, percent. It is distinct from sibling tools like get_homework or get_periods by focusing on grades. However, it does not explicitly contrast itself with other grade-related tools, so it doesn't fully achieve the top score for sibling differentiation.

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 provides clear context on when to use it (when you need grades) and mentions optional filters for year and term. It does not explicitly state when not to use it or point to an alternative, but the optional filter syntax gives operational guidance. Since it is a straightforward read operation, this is clear enough.

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