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

Annotations already declare read-only, but the description adds substantive context they cannot: the source of truth (user_topic_mastery keyed by identity+course+topic), the scoping model (learner/course-scoped, not chat/client-scoped), who writes vs reads the rows, and the meaning of an empty result ('no IP attempts yet, not a separate client score').

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-loads the purpose and return shape before the routing and scoping notes, which is the right order. It runs a bit long, with two adjacent sentences covering overlapping read-only/scoping claims, but nothing is truly 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?

For a single-param read tool with an output schema present, the description covers everything an agent needs: when to call it, what the fields mean, the empty-state interpretation, and the scoping/data-origin model. Nothing material is missing.

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% for the single course_id parameter and the schema already documents it fully as a positive course id. The description only restates 'Requires course_id', adding no syntax, format, or constraint detail beyond the structured field, so baseline 3 applies.

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?

Opens with a specific verb+resource ('Return practised-topic Infinite Practice mastery for a course') and enumerates exactly what comes back (topic_id, topic_name, display 0–100, questions_answered). It is clearly separable from neighbors like get-context and get-course-syllabus.

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?

States a concrete trigger: 'Use after get-context flags (has_course_mastery / started_course_mastery) or whenever context omitted topic_masteries.' This names the related tool and the condition that selects it, though the inverse case (skip it when get-context already supplied masteries) is only implied rather than stated.

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