problemsetProblemset + per-problem submission counts. Optional tag filter.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | e.g. ["dp","graphs"] | |
| problemset_name | No | Custom problemset (rarely used). |
| Name | Required | Description | Default |
|---|---|---|---|
| result | No | Problemset result | |
| status | Yes | Response status (OK or FAILED) | |
| comment | No | Error comment (if status is FAILED) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {},
+ {
+ "tags": [
+ "dp",
+ "graphs"
+ ]
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "comment": {
+ "description": "Error comment (if status is FAILED)",
+ "type": "string"
+ },
+ "result": {
+ "description": "Problemset result",
+ "properties": {
+ "problemStatistics": {
+ "description": "Submission statistics per problem",
+ "items": {
+ "properties": {
+ "contestId": {
+ "description": "Contest ID",
+ "type": "number"
+ },
+ "index": {
+ "description": "Problem index",
+ "type": "string"
+ },
+ "solvedCount": {
+ "description": "Number of solves",
+ "type": "number"
+ },
+ "totalSubmissions": {
+ "description": "Total submissions",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "problems": {
+ "description": "Array of problems",
+ "items": {
+ "properties": {
+ "contestId": {
+ "description": "Contest ID",
+ "type": "number"
+ },
+ "index": {
+ "description": "Problem index",
+ "type": "string"
+ },
+ "name": {
+ "description": "Problem name",
+ "type": "string"
+ },
+ "points": {
+ "description": "Points",
+ "type": "number"
+ },
+ "problemsetName": {
+ "description": "Problemset name",
+ "type": "string"
+ },
+ "rating": {
+ "description": "Difficulty rating",
+ "type": "number"
+ },
+ "tags": {
+ "description": "Problem tags",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "type": {
+ "description": "Problem type",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "status": {
+ "description": "Response status (OK or FAILED)",
+ "type": "string"
+ }
+ },
+ "required": [
+ "status"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and idempotent. The description adds that it returns per-problem submission counts and accepts an optional tag filter, which is transparent but minimal. No disclosure of performance or edge cases.
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?
Single sentence that is front-loaded with the main action and includes the key features. No redundant 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?
While an output schema exists and reduces the need to explain return values, the description lacks context about what 'problemset' refers to (e.g., from a specific platform) or how it relates to other tools. Adequate but not thorough.
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 descriptions for both parameters. The description adds the phrase 'Optional tag filter' to clarify the tags parameter and labels problemset_name as 'rarely used', providing additional nuance 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 clearly states it retrieves a problemset with per-problem submission counts and optional tag filtering. The verb is implied but clear from context. It distinguishes from siblings like contest_list or contest_standings by focusing on a problemset with submission counts.
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 guidance on when to use this tool versus alternatives like contest_standings or recent_actions. No mention of prerequisites, limitations, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The set mixes Codeforces-specific tools with a large Pipeworx data toolkit. Within the Pipeworx family, ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are nearly identical (the beta explicitly matches the stable version today), and deep_research/discover_tools/suggest_questions also overlap as meta entry points, creating real selection hazard. An agent could easily misselect among these.
Naming patterns are mixed: some tools use verb_noun (list_subscriptions, validate_claim, resolve_entity), some use bare verbs (remember, forget, recall), and some are noun phrases (problemset, blog_entry_view, recent_actions). Word order also varies (contest_list vs list_subscriptions), so no consistent convention is followed.
39 tools is far too many for a server named 'Codeforces' — only 8 tools actually concern Codeforces, while the remaining 31 are unrelated Pipeworx/utility tools. This bloats the surface and makes the server feel unfocused, especially for an agent expecting a compact Codeforces API.
For the Codeforces domain, the core read-only API is covered (contests, standings, problems, user info/rating/status, blog entries, recent actions) but some endpoints are missing (blog comments, rated list, problem statements). The large number of extra tools does not fill these gaps and instead obscures the intended purpose.