search_users

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

Given no annotations exist, the description must fully disclose behavioral traits. It clarifies that filtering is server-side via Moodle, not preloaded client-side, which is important for understanding performance and accuracy. It also explains the offset pagination (in the offset parameter description). However, it doesn't state what happens on error (e.g., invalid search field, empty result), or whether the tool is read-only/idempotent (implicitly yes, but not stated). Still, with no annotations, this is strong transparency.

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?

Three sentences, each packed with value: the first states purpose and searchable fields; the second provides usage context and behavioral fact; the third gives a critical usage guideline about filtering and handling multiple matches. No wasted words. Front-loaded with the essential purpose.

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?

Given the tool has 7 parameters, no output schema, and no sibling tool that does exactly the same (only get_user for specific ID), the description covers usage, behavior, and the key parameter nuance (offset). It does not explain return format or what happens when multiple fields are provided (priority or conjunction), which could be needed for complete understanding. But for a search tool, it is largely sufficient. A 5 would require documenting the return structure or combining logic.

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%, so baseline is 3. The description does not repeat parameter schemas but adds value by explaining the offset behavior ('applied after Moodle returns matches') which clarifies pagination semantics that the schema alone does not. It also stresses the requirement to provide 'at least one standard Moodle search field', implying that the tool may fail or return no results if used without any filter, which is not obvious from the optional schema. One could argue for a 5, but the score stays at 4 because the added value is not exhaustive (e.g., no guidance on combining multiple fields).

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 'Search' and the resource 'Moodle users', and lists the specific search fields (firstname, lastname, email, username, idnumber). This distinctively differentiates it from siblings like list_courses, get_user (which may require a user ID), or list_course_users (which filters by course). The scope is precise.

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 explicitly says 'Use this for direct person lookup, not structured directory filtering or reports.' It provides a prerequisite ('Provide at least one standard Moodle search field'), explains behavior ('Moodle performs the filtering first; this tool does not preload the full user directory'), and names an alternative ('If a directory listing plugin is installed, prefer that plugin for filter-style requests'). It also warns against premature downstream actions when multiple matches occur. This is exemplary guidance.

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