Wellemo — online tests and quizzes

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

Annotations only declare the generic write/open-world profile; the description goes far beyond them by explaining the three returned URLs, the privacy asymmetry between take_url and edit_url, and the side effect that opening edit_url while logged in saves the test to the account. That last detail is a non-obvious behavioral consequence an agent could not infer from structured fields.

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 action, then behavior, then return values, then mandatory post-call instructions — a sensible priority order with no filler. The opening sentence is somewhat run-on and could be split, but every clause carries information.

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 7-parameter creation tool with no output schema, the description covers the essential gaps: what is produced (three URLs), what the agent must do with them, privacy constraints, and the question-count ceiling. An agent can call this correctly and report results without further inference.

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 86%, so the enum values, question types, matching pairs, tolerance, and pass_score semantics are already fully documented in the schema. The description adds only the 100-question cap (already encoded as maxItems) and the instruction to write questions in the user's language; it says nothing extra about time_limit, show_answers, or pass_score behavior.

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?

States a specific verb and resource — create an online knowledge test / exam-style quiz with scoring on Wellemo — plus scope (questions you write, shareable link). The action is unmistakably distinct from get_test_results and search_tests, though the description never names those siblings to route the agent explicitly.

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?

Gives concrete operating context: participants take it in the browser without registration, write questions in the user's language, up to 100 questions, and always surface take_url/edit_url while keeping edit_url private. It stops short of telling the agent when NOT to use it or pointing at search_tests to check for existing tests.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-derived behavior: participant names are withheld and full results live at results_url, which shapes how the agent should present output. It doesn't mention access control or error behavior for an invalid or non-owned edit_url.

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?

Two sentences, front-loaded with purpose and return contents, followed by the input provenance and an output caveat. No filler and nothing repeated from structured fields.

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?

With no output schema, the description carries the burden of describing return values, and it does so concretely (participant count, average score, pass rate, average time, top missed questions) while pointing to results_url for detail. For a one-parameter read tool, this is complete enough to invoke correctly.

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 parameter, so the baseline is 3. The description goes beyond the schema by explaining that the edit_url is private, that an id extracted from it also works, and which sibling tool produced it — useful semantics the schema does not convey.

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?

States a specific verb (get) and resource (results for a Wellemo knowledge test) and enumerates exactly what the summary contains: participants, average score, pass rate, average time, and most-missed questions. Clearly not test creation (create_knowledge_test) or discovery (search_tests), so the agent can select it without opening schemas.

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?

Specifies the prerequisite and provenance of the required input: the private edit_url (or its id) returned by create_knowledge_test, which establishes the create-then-read workflow. It does not explicitly exclude or compare against search_tests for different result-retrieval scenarios, so it stops short of full alternative routing.

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

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses exactly what is returned: titles, short descriptions, take counts, and a link to take each test. It also warns that questions are not returned and instructs the agent to give the user the links, which is meaningful behavioral guidance for generating a response. It does not cover edge cases such as empty results, so it is strong but not exhaustive.

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 three sentences, front-loaded with the core action and scope. Every sentence adds value: the first states what is searched, the second states what is returned, and the third prevents the agent from expecting question content and tells it how to respond.

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 two-parameter read-only search tool with no output schema, the description covers the essential context: the catalog being searched, the fields returned, the fact that questions are excluded, and the instruction to provide links. It does not mention empty-result handling or pagination behavior, but no output schema exists and the remaining gaps are minor.

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 the schema already documents both query and limit, including the default and maximum for limit. The description adds only the topic framing for query and does not add format, syntax, or matching semantics beyond what the schema provides.

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 states a specific verb and resource: 'Search the public Wellemo catalog of ready-made tests and quizzes by topic.' That is far more informative than the name alone and clearly distinguishes this from create_knowledge_test and get_test_results by emphasizing a read-only catalog search. It stops short of explicitly naming or contrasting the sibling tools, so a 4 rather than a 5.

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 makes the intended use clear: search by topic to find ready-made tests, then give the user the links. It does not explicitly state when not to use this tool or point to an alternative, but the surrounding context makes the appropriate use case obvious.

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