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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false, so the safety profile is largely covered. The description adds genuinely new behavior: an existing file is not overwritten and a "(1)" suffix is appended, which also explains the non-idempotent hint. Auth/site prerequisites are not mentioned, but nothing contradicts the annotations.

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 and return value, then the input provenance, then the overwrite caveat — each sentence earns its place. Slightly compressed/awkward in the final clause (the quote around "(1)"), but no wasted content.

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 side-effecting download with no output schema, the description covers the return value, the required input's source, and the collision behavior. Only minor gaps remain: no mention of permissions or failure modes when the URL is unreachable.

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 baseline is 3, and the description goes beyond it by identifying fileUrl's provenance (the url field from the listing/submission tools). destDir's create-if-missing behavior is already in the schema, so the description adds value on one parameter only.

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 (downloads a submission file / assignment attachment to local disk) and names the return value (its path). It also references the sibling tools that produce the required input, so an agent can place it precisely against moodle_get_submission and moodle_list_assignments.

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?

Explicitly tells the agent where fileUrl comes from — the url field of moodle_get_submission or moodle_list_assignments — which is real routing guidance rather than implied usage. It stops short of stating when NOT to use it or any prerequisite/ordering constraints.

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 cover the safety profile (readOnlyHint, idempotentHint, openWorldHint), so the bar is lower. The description still adds real behavioral context: the payload shape, that online text is delivered as plain text, and that file entries carry a url intended for moodle_download_file — useful chaining information beyond the annotations.

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?

A single dense sentence that front-loads the resource and then lists return fields in a scannable order. No filler and nothing repeated from the schema.

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?

There is no output schema, so the description properly carries the return-value burden and does so thoroughly. The only gap is the not-found case — it does not say whether a missing submission yields an error or an empty 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%, and the schema already explains both userId (from moodle_list_submissions) and assignmentId (the id field, not the cmid). The description adds nothing about parameters, so the 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?

The description names the exact resource (one participant's full submission) and enumerates its contents: status/attempt number, time, online text, files, grade and feedback. The singular 'one participant' implicitly separates it from the sibling moodle_list_submissions, but it never states that distinction or uses an explicit retrieval verb.

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?

No when-to-use guidance is given, and no alternative is named. The agent must infer that this is the drill-down after moodle_list_submissions and that moodle_download_file is the follow-up for the file URLs; neither is stated as a usage rule.

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, idempotentHint and openWorldHint, so the safety profile is covered. The description adds no behavior beyond that — no ordering, pagination, or how hidden/completed courses affect results — only a field inventory, which belongs to output documentation.

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?

One dense, front-loaded sentence that enumerates the returned fields without filler. The parenthetical about cmid's URL origin aids comprehension, though the long comma-separated enumeration mildly reduces scannability.

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 return-value burden and does so by listing id, cmid, name, dates, grading and submission types — enough for an agent to use the result. It stops short of noting ordering or whether all assignments or only visible ones are returned.

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?

There is a single parameter (courseId) with 100% schema description coverage including its origin (moodle_list_courses or the view.php URL). The description adds no parameter meaning beyond the schema, so the 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?

The description identifies the resource precisely ('Assignments of a course (Assignment activity, mod_assign)') and hints at scope, so an agent can tell it apart from moodle_list_submissions and moodle_get_submission. It lacks an explicit verb ('List'), relying on the tool name to supply the action, which keeps it short of 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?

'assignment id (needed by the other tools)' implies this is a prerequisite lookup step before calling sibling tools, which is useful implied usage. There is no explicit when-to-use/when-not statement and no named alternative (e.g. use moodle_list_submissions for submission data), so guidance stays 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.

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), so the bar is lower. The description adds useful scope context (self-enrolled, including teacher role), but says nothing about pagination, result size limits, or auth requirements.

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 dense sentences with no filler; the core purpose is front-loaded and the field list follows. 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?

With no output schema, the description valuably enumerates the returned fields (id, short/full name, dates, visibility). The main remaining gap is pagination or result-count behavior, but for a zero-parameter read tool this is otherwise complete.

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 tool takes zero parameters, so the baseline of 4 applies. No parameter-level meaning is needed, and the description correctly avoids inventing options.

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 precise verb+resource ('List my courses on the Moodle site') and even clarifies enrollment scope ('including as a teacher'), which distinguishes it from an admin-style course listing. It also names the downstream relationship to moodle_list_assignments.

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 implies usage by noting the course id is needed for moodle_list_assignments, but it never states when to prefer this tool over siblings like moodle_site_info or any exclusions. Guidance is implied rather than explicit.

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 cover readOnly/idempotent/openWorld, so the safety profile is free. The description earns credit by decoding the state machine (new = not submitted, reopened = new attempt opened) and clarifying that status narrows the list while counts summarizes everyone — behavioral context beyond the annotations, though it stops short of pagination or volume limits.

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 resource and return fields, and compact at roughly three sentences. The phrase 'counts summarizes all participants' is a minor blemish because no counts parameter or output is defined in the schema, making that clause slightly confusing rather than useful.

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 does the necessary work of naming the fields returned and describing the filter's effect on the result set. It is largely sufficient for a two-parameter read tool, with the ambiguity around 'counts' being the only notable gap.

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 both parameters are already documented, and the description only restates that the status filter narrows the list. Baseline 3 applies since the schema carries the semantic load, including the crucial assignmentId-vs-cmid distinction.

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 names the resource (assignment participants) and enumerates the returned fields (status, submission time, needs-grading flag, current grade), so an agent knows exactly what this tool yields. It lacks an explicit verb (e.g. 'list') and a stated scope, but the closing contrast with moodle_get_submission makes the boundary unambiguous.

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 sentence 'moodle_get_submission returns one participant's full submission' implicitly routes the agent: use this for the roster, the sibling for a single person. However, it never states when-not to use it, nor does it mention siblings like moodle_list_assignments (for ids) explicitly as prerequisites despite the schema referencing it.

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 flag destructive/non-idempotent/open-world, and the description adds consequences the annotations cannot express: the student will see the grade and feedback (immediately or after release under marking workflow), a notification may fire, the grade is validated against the assignment maximum, and omitted feedback is preserved rather than cleared.

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?

Five short sentences, each carrying a distinct obligation (effect, visibility, precondition, validation, feedback-default), with the highest-stakes fact ('THE STUDENT WILL SEE') emphasized early.

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 9-parameter destructive mutation with no output schema, the description covers the write's side effects, the release/notification path, validation behavior, and the confirmation prerequisite. Nothing needed to invoke it safely 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 description coverage is 100%, so the baseline is 3. The description echoes two points already in the schema (grade checked against the maximum, omitted feedback retained) but adds no syntax or format detail for parameters like workflowState, addAttempt, or applyToAll beyond what the schema states.

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 ('Saves a participant's grade for an assignment') plus the secondary write ('writes feedback comments'), which is unambiguous next to the read-only siblings like moodle_get_submission and moodle_list_submissions.

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 a firm precondition: 'Call only after the teacher has explicitly confirmed the grade and the text,' which is exactly the kind of gating guidance a write tool needs. It does not name an alternative tool for correcting or deleting a grade, but sibling read tools are clearly not substitutes here.

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 cover the safe-read profile (readOnly, idempotent, openWorld), so the description's value-add is the missingFunctions semantics — API functions the token lacks, and the consequence that dependent tools will fail. That is meaningful behavioral context beyond the structured fields; it stops short of describing the shape of the returned payload.

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?

A single dense sentence with the payload inventory front-loaded after the colon and the usage trigger placed last. Every clause carries information; nothing is redundant.

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 return-value burden and does so by listing the fields, including the non-obvious missingFunctions. It omits the exact format/content of missingFunctions entries, a minor gap for a zero-parameter diagnostic tool.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 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?

States a specific verb-like purpose (retrieve identity and site metadata) and enumerates exactly what is returned: user name/id, site name, Moodle version, MCP server version, and missingFunctions. It is clearly distinguishable from the sibling list/get tools, which deal with courses, assignments, and submissions.

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?

Explicitly says to 'start here if it is unclear whether the connection works', giving a concrete trigger for invocation. It does not name alternative or exclusionary tools, but the diagnostic framing is enough to route the agent correctly.

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