Skip to main content
Glama

Programscape

by com.programscape
OverviewDiscussionsAdmin

Save the founder’s review

save_plan_draft

Saves a founder’s review as a one-day draft and returns a link that opens it on programscape.com with their answers and kept programs in place. The founder saves it there with an email code (no password). The link works for 24 hours.

Input Schema

NameRequiredDescriptionDefault
keepNoIds of programs the founder chose to keep. Empty or left out when they chose none.
answersYesThe founder’s answers, keyed by question field: the shared questions’ fields or a question a review returned (e.g. "stage": "seed", "funding": ["venture"], "currentProviders": ["aws", "openai"], "companyTypes": ["ai"]). A fact the founder hasn’t given is left out and stays unknown.
inferredAnswersNoThe worked-out partner answers a saved plan returned as inferredAnswers, exactly as returned: the review reads them as Programscape worked them out, not as the founder’s own answers, and one from a list that has changed since as unanswered.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / answers / additionalProperties / anyOf
      Previous value: -[
-  {
-    "maxLength": 200,
-    "type": "string"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "items": {
-      "maxLength": 80,
-      "type": "string"
-    },
-    "maxItems": 30,
-    "type": "array"
-  }
-]New value: +[
+  {
+    "maxLength": 200,
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  },
+  {
+    "type": "null"
+  },
+  {
+    "items": {
+      "anyOf": [
+        {
+          "maxLength": 80,
+          "type": "string"
+        },
+        {
+          "type": "boolean"
+        }
+      ]
+    },
+    "maxItems": 30,
+    "type": "array"
+  }
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / inferredAnswers
      Added value: +{
+  "description": "The worked-out partner answers a saved plan returned as inferredAnswers, exactly as returned: the review reads them as Programscape worked them out, not as the founder’s own answers, and one from a list that has changed since as unanswered.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "answer": {
+        "const": "yes",
+        "type": "string"
+      },
+      "field": {
+        "maxLength": 80,
+        "type": "string"
+      },
+      "listDated": {
+        "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+        "type": "string"
+      }
+    },
+    "required": [
+      "field",
+      "answer",
+      "listDated"
+    ],
+    "type": "object"
+  },
+  "maxItems": 20,
+  "type": "array"
+}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint false, destructiveHint false, idempotentHint false), and the description usefully adds traits the annotations cannot convey: the artifact is a temporary draft with a 24-hour lifetime, completion requires an email code rather than a password, and the founder's answers and kept programs are carried into the link. It does not warn that repeated calls are non-idempotent and may produce multiple drafts, which is the main residual gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and outcome, then the founder-side step and the expiry. Every sentence contributes a distinct fact — what is created, how it is opened, and how long it lasts — with no filler or restated name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema present, the description correctly carries the return value itself (a link) and its lifetime, and it explains the human hand-off step that distinguishes this tool from a normal write. Missing only the failure/repeat-call semantics an agent would want before invoking a non-idempotent create.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 and the schema already explains all three parameters in depth. The description adds only a light restatement ('with their answers and kept programs in place', 'exactly as returned' for inferred answers) and says nothing extra about how to source or format inferredAnswers beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource — saving a founder's review as a one-day draft — plus the distinctive outcome (a 24-hour link that opens on programscape.com with answers and kept programs preserved). That is far more precise than the title alone. It never names or contrasts with the closest siblings (my_plan, update_my_plan), so an agent must infer the boundary itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the description makes clear this is a hand-off step (the founder finishes it themselves via an email code), which suggests calling it at the end of a review rather than for persisting a finished plan. There is no explicit when-to-use, no when-not-to-use, and no pointer to update_my_plan or my_plan for the alternative paths.

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

All Programscape toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources