DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Average 4.2/5 across 10 of 10 tools scored. Lowest: 3.5/5.
The tools map well to distinct resources and workflow stages, and the async flows are clearly explained. The main overlap risk is paper_create/paper_confirm and markResult_get/submission_get, where names point at similar actions but the descriptions make the boundaries usable.
Most names follow the same resource_action snake_case pattern, e.g. paper_get, submission_mark, markScheme_update. markResult_get breaks the pattern slightly by mixing camelCase into an otherwise snake_case set, but the naming stays readable and predictable overall.
Ten tools is a well-scoped size for this domain: paper creation, confirmation, retrieval, question/mark-scheme correction, and submission grading are covered without excess granularity or obvious filler.
The main end-to-end workflow—create extraction job, confirm paper, mark submission, poll results—is complete and coherent. Minor gaps exist, such as no paper deletion, no submission listing, and no direct way to fetch a mark scheme separately, but they are not blocking for the core grading loop.
ingestion_getGet Ingestion Job StateARead the current state of an ingestion job (paper creation or document ingestion). Returns the status plus a derived awaiting gate ('triage' | 'confirmation' | null), whether it is terminal, and the next action to take. Poll this after starting a job: a paper-creation job parks at awaiting_confirmation (then call paper_confirm) — it does NOT run to complete on its own. Stop polling on a terminal status (complete | failed | cancelled) or when an action is required.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | ID of the ingestion job to read the current state of. |
| Name | Required | Description |
|---|---|---|
| kind | Yes | The ingestion job kind (paper_bundle, student_batch, source_document, …). |
| error | Yes | Failure detail, when status is failed. |
| job_id | Yes | |
| status | Yes | Raw ingestion status. |
| awaiting | Yes | The gate the job is parked at, or null if none. |
| terminal | Yes | True once the job will not change on its own. |
| created_at | Yes | ISO-8601 creation timestamp. |
| needs_action | Yes | Human-readable next step for the caller. |
| processed_at | Yes | ISO-8601 completion timestamp, or null if not yet processed. |
| attempt_count | Yes | Processing attempts so far. |
| exam_paper_id | Yes | The minted paper's id, once one exists. |
| triage_summary | Yes | Triage explanation, only while parked at the triage gate. |
| triage_issue_count | Yes | How many triage issues, only while parked at the triage gate. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the readOnlyHint and idempotentHint annotations by disclosing derived state (awaiting gate), the parking behavior of paper-creation jobs, and terminal statuses. It also tells the caller when to stop polling, which is critical operational context not present in annotations. No contradictions with 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?
The description is four sentences, front-loaded with purpose and return values, then usage instructions. Every sentence adds unique value: purpose, return contents, polling guidance, and termination criteria. No fluff or repetition of schema/annotations.
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's moderate complexity (state machine, polling, cross-tool action), the description covers the full usage lifecycle: when to call, what to expect, when to stop, and what to do next. The presence of an output schema handles return format details, so the description is complete for the agent's invocation decision.
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% for the single parameter job_id, so the schema fully documents it. The description adds no additional parameter semantics beyond reaffirming that this is a polling operation. Baseline 3 is appropriate as the schema carries the burden.
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 'Read' and the resource 'current state of an ingestion job', distinguishing it from sibling getters like paper_get and submission_get by scoping to ingestion jobs. It also specifies the returned fields (status, awaiting gate, terminal, next action), making the tool's purpose 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?
Explicitly says 'Poll this after starting a job' and provides concrete stopping conditions (terminal status or when action is required). It also names the next action for paper-creation jobs (call paper_confirm) and warns that such jobs do not run to complete on their own. This is clear when/where-to-use guidance, including an alternative (paper_confirm) for the follow-up step.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
markResult_getGet Mark Result by Answer IDARetrieve the marking result for a specific answer by its ID
| Name | Required | Description | Default |
|---|---|---|---|
| answer_id | Yes | The unique identifier for the answer to retrieve the marking result for |
| Name | Required | Description |
|---|---|---|
| answer_id | Yes | |
| marked_at | Yes | ISO-8601 timestamp the mark was recorded. |
| mark_points | Yes | Per-mark-point decisions (point_based questions); [] otherwise. |
| mark_scheme | Yes | |
| total_score | Yes | |
| llm_reasoning | Yes | |
| feedback_summary | Yes | |
| max_possible_score | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is known. The description adds no extra behavioral traits such as error handling for missing IDs or side effects, providing no value 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?
The description is a single, concise sentence with no redundant words. It is front-loaded with the action and resource, making it easy to parse.
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 simple read-only lookup with one parameter, an output schema, and good annotations, the description is fully adequate. It clearly states the purpose, and the output schema covers return values, so nothing essential 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% with a clearly described answer_id parameter, so the schema fully documents the parameter. The description does not add additional meaning or context for the parameter, earning the baseline score of 3.
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 tool retrieves a marking result for a specific answer by ID, using the verb 'Retrieve' and identifying the resource. It distinguishes itself from sibling get tools like submission_get and paper_get by specifying 'marking result'.
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 no guidance on when to use this tool versus alternatives, nor does it mention exclusions or complementary tools. The sibling list contains other getters, but no differentiation is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
markScheme_updateUpdate Mark SchemeAUpdate an existing mark scheme by its ID
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The unique identifier for the mark scheme to update | |
| content | No | The full mark scheme content text (level descriptors, caps, guidance, etc.) | |
| mark_points | No | Array of mark points | |
| points_total | No | Total number of points for the mark scheme | |
| marking_method | No | How to mark: deterministic (MCQ), point_based, or level_of_response |
| Name | Required | Description |
|---|---|---|
| updated | Yes | Names of the fields written by this call. |
| question_id | Yes | |
| points_total | Yes | |
| mark_scheme_id | Yes | |
| mark_point_count | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is a mutating (readOnlyHint=false), idempotent operation. The description adds no behavioral context beyond restating the action; it does not clarify partial vs. full update, error handling, or overwrite behavior.
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 a single concise sentence: 'Update an existing mark scheme by its ID.' No wasted words; action, resource, and scope are front-loaded.
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?
The description is minimal but paired with a detailed schema and annotations. However, it lacks clarity on update semantics (e.g., partial vs. full replacement, what happens if ID not found), so it is adequate but has gaps.
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 schema already documents all parameters. The description itself adds no parameter-level detail, hence the baseline score of 3.
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 action (update), the resource (mark scheme), and the scope (existing, by ID). It distinguishes from siblings like 'paper_create' and 'question_update'.
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: it updates existing mark schemes. However, it does not explicitly mention alternatives or when not to use this tool, such as referencing paper_create for new mark schemes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
paper_confirmConfirm Exam Paper DraftAMint the exam paper from a job parked at awaiting_confirmation (created via paper_create). Materialises the ExamPaper, questions, and mark schemes from the extraction draft, synchronously. Optionally override the detected identity (title/subject/board/year); omit to use what extraction detected. Idempotent — confirming an already-committed job returns its paper. Returns the exam_paper_id.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | ID of the ingestion job to confirm. Must be parked at awaiting_confirmation (poll ingestion_get first). | |
| metadata | No | Optional identity overrides. Omit to mint the paper with the identity detected during extraction. `total_marks` is always derived from the question marks — never supplied here. |
| Name | Required | Description |
|---|---|---|
| status | Yes | Terminal status of the paper (complete). |
| outcome | Yes | "created" on first confirm, "already committed" on re-confirm. |
| view_with | Yes | The tool to inspect the paper with (paper_get). |
| exam_paper_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare idempotentHint=true, and the description reinforces this with 'confirming an already-committed job returns its paper.' It adds the behavioral detail that the materialization is synchronous and that the operation persists ExamPaper, questions, and mark schemes. It also mentions the return of exam_paper_id, which is beyond the annotation set.
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 four sentences and front-loaded with the main verb and subject. Each sentence carries a distinct piece of information—purpose, materialization, overrides, idempotency, and return value—with no filler.
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?
Covers the workflow context (paper_create, awaiting_confirmation), the synchronous materialization, override semantics, idempotent behavior, and return value. The schema supplies parameter-level detail and the output schema exists, so the description is comprehensive for its complexity.
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 schema already provides 100% coverage for both parameters, including per-field descriptions for every metadata override. The description adds only a high-level summary ('Optionally override the detected identity') without additional per-parameter detail, so it doesn't add significant meaning beyond the schema.
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 opens with a specific verb-resource combination—'Mint the exam paper'—and anchors it to a concrete workflow step ('job parked at awaiting_confirmation'). It distinguishes itself from siblings by naming paper_create as the precursor and describing the materialization of ExamPaper, questions, and mark schemes.
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?
It explicitly states the precondition ('job parked at awaiting_confirmation') and references paper_create as the source workflow. It explains the optional override behavior and says to omit it to use extraction-detected identity. It does not explicitly list exclusions (e.g., 'do not use if the job is still processing'), but the awaiting_confirmation requirement is a clear gate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
paper_createCreate Exam Paper from TextAInspectCreate a complete, markable exam paper from pasted text. Provide the question paper text (required) and, if the teacher has one, the mark scheme text — DeepMark extracts it. Omit the mark scheme to have DeepMark generate schemes (lower quality, but the paper is still markable). Send RAW text: do not pre-structure it into questions or author a mark scheme yourself. Extraction runs asynchronously — this returns a job_id. Poll ingestion_get until it reaches awaiting_confirmation, then call paper_confirm to mint the paper. RATE LIMITED: up to 3 papers per 24 hours per account (marking existing papers is unaffected).
| Name | Required | Description | Default |
|---|---|---|---|
| hints | No | Optional cover-identity hints. SOFT grounding for extraction — they steer the model, they do not override the paper text. | |
| stimulus_text | No | Optional source/stimulus material the questions refer to (a passage, dataset, case study). Supplied as extraction context; it is not itself turned into questions. | |
| mark_scheme_text | No | RAW text of the mark scheme, if the teacher has one. Read jointly with the question paper so marks and numbering align. Send raw text, NOT a mark scheme you authored. Omit entirely when there is no mark scheme — DeepMark generates one per question (lower quality than a real scheme, but the paper is still markable). | |
| question_paper_text | Yes | RAW text of the question paper — questions, bracketed marks, section headers, as printed or pasted. Send the source text and let DeepMark extract the questions. Do NOT pre-structure it into questions yourself. |
| Name | Required | Description |
|---|---|---|
| job_id | Yes | |
| status | Yes | The job's initial status (pending). |
| poll_with | Yes | The tool to poll this job with (ingestion_get). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (which only state this is not read-only), the description discloses that extraction runs asynchronously, returns a job_id, and is rate-limited to 3 papers per 24 hours. It also candidly notes the quality tradeoff when the mark scheme is omitted, adding meaningful behavioral context.
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 a single dense paragraph that front-loads the core action, then efficiently covers the workflow, raw-text caveats, and rate limits. Every sentence contributes necessary information with no redundancy, making it concise yet complete.
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 complex tool with async behavior, a multi-step workflow, and rate limits, the description covers the entire lifecycle: input requirements, asynchronous job creation, polling, confirmation, and quality considerations. The existence of an output schema means return values need not be spelled out, and this description fills all contextual gaps.
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?
All 4 parameters are already covered by schema descriptions (100% coverage), so the description adds little parameter-level detail. It reinforces that the question paper text is required and explains the consequence of omitting the mark scheme, but those points are also present in the schema, keeping this at the baseline of 3.
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 opens with 'Create a complete, markable exam paper from pasted text,' clearly stating the verb and resource. It distinguishes itself from sibling tools like paper_confirm by explaining that this tool returns a job_id and that paper_confirm mints the paper, so the purpose is 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 description gives explicit when-to-use guidance: send RAW text, do not pre-structure it, and omit the mark scheme only if you want DeepMark to generate one. It also provides the full async workflow—poll ingestion_get until awaiting_confirmation, then call paper_confirm—and notes the rate limit, which differentiates it from marking tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
paper_getGet Exam Paper by IDARetrieve a specific exam paper by its ID with question details
| Name | Required | Description | Default |
|---|---|---|---|
| exam_paper_id | Yes | The ID of the exam paper to retrieve |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| tier | Yes | |
| year | Yes | |
| title | Yes | |
| subject | Yes | |
| sections | Yes | |
| created_at | Yes | ISO-8601 creation timestamp. |
| created_by | Yes | |
| exam_board | Yes | |
| total_marks | Yes | |
| paper_number | Yes | |
| duration_minutes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry the key behavioral safety profile: readOnlyHint=true and idempotentHint=true, so an agent knows this has no lasting side effects. The description adds the 'with question details' scoping fact, which is useful. It does not comment on permissions, errors, or response shape beyond that, so the description adds only a modest amount 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?
The description is a single focused, front-loaded sentence. It names the action, the object, the identifier criterion, and the expected content detail with no filler or redundancy.
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?
This is a simple read-only tool with one parameter and an output schema, so the description does not need to explain return values or data structures. The core intent of retrieving a specific exam paper with question details is fully captured, making the definition complete for an agent to invoke it 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%: the only parameter, exam_paper_id, is already fully described in the schema with 'The ID of the exam paper to retrieve.' The description does not add any extra parameter information beyond echoing the ID-focused purpose. Thus, it earns the baseline score for schema-covered parameters.
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 a specific verb ('Retrieve'), the resource ('exam paper'), and the selection criterion ('by its ID'). It also adds 'with question details', which distinguishes the returned content from what paper_list would provide. An agent can unambiguously tell this from sibling tools like paper_create or paper_list.
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 implicitly communicates the correct usage: use this tool when you already know the exam paper ID and need the full paper with questions. It does not explicitly name alternatives or exclusions, but the context of retrieving a specific paper by ID is clear enough given sibling tools like paper_list suggest searching/listing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
paper_listList Exam PapersAList all exam papers with optional filtering
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of papers to return (pagination page size). | |
| offset | No | Number of papers to skip before returning results (pagination). | |
| subject | No | Filter to a single subject. |
| Name | Required | Description |
|---|---|---|
| limit | Yes | |
| offset | Yes | |
| papers | Yes | |
| has_more | Yes | True when a full page came back — request the next offset. |
| returned | Yes | How many papers this page returned. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and idempotent behavior, so the description does not need to repeat those. However, the description adds little beyond that—no detail about what is included in the list or constraints like pagination behavior, which could be useful context.
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 a single, direct sentence that communicates the tool's purpose with no unnecessary words. It earns its place without redundant phrasing or over-explanation.
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?
The description is sufficient for a simple list operation, and both input and output schemas provide strong structural context. Minor gaps include not explicitly stating pagination implications, but these are already well documented in the schema.
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 input schema has 100% coverage, with descriptions for limit, offset, and subject. The description's 'optional filtering' hints at the subject filter but does not add meaningful meaning beyond what the schema already 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 clearly states the action ('List') and the resource ('exam papers'), and adds scope with 'all' and 'optional filtering'. This effectively differentiates paper_list from siblings like paper_get (single retrieval) and paper_create (creation).
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 this tool is for listing papers with optional filters, but it does not explicitly state when to use this tool versus alternatives like paper_get or paper_confirm. There are no exclusionary conditions or comparative guidance provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
question_updateUpdate Question by IDAUpdate an existing GCSE question by its ID
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The unique identifier for the question to update | |
| topic | No | The topic or subject matter for the question | |
| points | No | Number of marks the question is worth | |
| subject | No | Subject area for the question | |
| question_text | No | The exam question | |
| difficulty_level | No | Difficulty level of the question |
| Name | Required | Description |
|---|---|---|
| topic | Yes | |
| points | Yes | |
| subject | Yes | |
| updated | Yes | Names of the fields written by this call. |
| question_id | Yes | |
| difficulty_level | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already provide safety information (readOnlyHint=false, destructiveHint=false, idempotentHint=true). The description adds no additional behavioral context, such as whether the update is partial or how missing fields are handled, providing minimal value beyond the structured 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?
The description is a single, direct sentence that immediately conveys the verb, resource, and identifier without any superfluous words. It is perfectly concise and well-structured.
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?
The tool is well-supported by a complete schema, meaningful annotations, and an existing output schema. The description, while brief, is sufficient for an agent to understand the tool's purpose and invoke it correctly. There is a minor gap in explicit usage guidance, but overall completeness is high.
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 schema fully describes all six parameters with individual descriptions, and the description does not add parameter-specific information beyond mentioning the ID. With 100% schema coverage, the baseline score of 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 clearly states the tool's function: 'Update an existing GCSE question by its ID.' It uses a specific verb ('update') and resource ('GCSE question'), and identifies the required identifier ('by its ID'), distinguishing it from sibling tools like markScheme_update or paper_confirm.
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 the tool is for modifying an existing question, which is a clear context. However, it does not explicitly mention alternatives or exclusions. Since no sibling tool updates questions, the context is sufficient, but it lacks explicit guidance on when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
submission_getGet Submission Grading ResultARead the grading state and per-question marks for a submission (created via submission_mark). Returns each question's marking_status, awarded/max marks, level, and feedback, plus an overall status ('grading' until every question is marked). Poll after submission_mark.
| Name | Required | Description | Default |
|---|---|---|---|
| submission_id | Yes | ID of the submission to read grading results for. |
| Name | Required | Description |
|---|---|---|
| status | Yes | Overall grading status. |
| questions | Yes | |
| total_max | Yes | Total marks available, null until grading is complete. |
| student_name | Yes | Detected student name, or null if none was read. |
| exam_paper_id | Yes | |
| grading_error | Yes | Failure detail when status is failed. |
| submission_id | Yes | |
| total_awarded | Yes | Total marks awarded, null until grading is complete. |
| questions_marked | Yes | Progress as "marked/total", e.g. "3/6". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, and the description adds behavioral details: it reveals the polling nature ('Poll after submission_mark') and explains the overall status transition ('grading' until every question is marked), which goes 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?
Two sentences, front-loaded with the core action, and no wasted words. The first sentence explains what is returned, and the second gives usage guidance. Every word earns its place.
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 read-only, single-parameter tool with annotations and a detailed description of return values, this is complete. The description mentions each question's marking_status, marks, level, feedback, and overall status, which is sufficient for an agent to understand the call and interpret results.
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 sole parameter submission_id is fully described in the schema (100% coverage), so the baseline is 3. The description adds value by linking the ID to a submission created via submission_mark, giving the agent practical context about where the ID comes from.
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 opens with 'Read the grading state and per-question marks for a submission', giving a specific verb ('read') and resource (submission grading result). It clearly distinguishes itself from sibling tools like submission_mark (which creates) and markResult_get (which may read a different result).
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 states the tool is for submissions 'created via submission_mark' and instructs to 'Poll after submission_mark', providing a clear when-to-use context. It does not explicitly discuss alternatives or exclusions, but the relation to submission_mark effectively frames its intended use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
submission_markMark a Student Submission from TextAInspectMark a student's typed answers against an existing exam paper. Provide the exam_paper_id and per-question answers keyed by question_number. DeepMark creates a submission and grades it through its canonical marker (per mark point / level descriptor) — results stream into the teacher's editor live. Grading is asynchronous: this returns a submission_id; poll submission_get for the per-question grades.
| Name | Required | Description | Default |
|---|---|---|---|
| answers | Yes | One entry per answered question, keyed to its question by number. DeepMark grades each answer against that question's mark scheme via the canonical marker. | |
| student_name | No | The student's name, surfaced in results. Optional. | |
| exam_paper_id | Yes | The exam paper to mark these answers against. |
| Name | Required | Description |
|---|---|---|
| poll_with | Yes | The tool to poll this submission with (submission_get). |
| exam_paper_id | Yes | |
| submission_id | Yes | |
| answers_submitted | Yes | How many answers matched a question and were queued for grading. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (which only indicate it's not read-only), the description discloses that DeepMark creates a submission, grades via the canonical marker (per mark point/level descriptor), streams results live to the teacher's editor, and is asynchronous, returning a submission_id. This is substantial behavioral context that aids the agent in understanding side effects and expected flow.
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, each serving a purpose: stating the action, specifying required inputs, and explaining the asynchronous outcome. It is front-loaded with the core purpose and wastes no words.
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 that an output schema exists (so return values don't need explanation), the description covers all necessary context: what the tool does, what inputs are needed, that grading is asynchronous, and what to do next (poll submission_get). It is complete for a tool of this complexity.
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 schema already describes all three parameters clearly, so baseline is 3. The description adds meaning by explaining how answers are keyed to question_number (as printed) and that grading is done per mark point/level descriptor. This enhances understanding beyond the raw schema without being redundant.
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 'Mark' and the resource 'a student's typed answers against an existing exam paper.' It distinguishes from siblings like submission_get, which retrieves grades, and paper_get, which fetches papers. The title and opening sentence align, leaving no ambiguity.
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 gives clear context: use when you have an exam_paper_id and per-question answers. It suggests polling submission_get for results, which implies an alternative, though it doesn't explicitly say 'do not use this for retrieving grades.' This provides usable guidance without a full exclusion list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as io.github.alice/server, link the matching GitHub user or an account that owns the GitHub organization, then choose Claim with GitHub.
HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at /.well-known/glama.json on the same origin as the connector, then choose Check HTTP challenge.
DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
