Skip to main content
Glama

PitchSpark: Pre-Seed & Seed Startup Pitches

Founders only: create a draft of your own startup pitch on PitchSpark

pitchspark_submit_pitch_v1

For founders: create a DRAFT startup pitch on the signed-in founder's own PitchSpark account from five facts: company name, sector, funding stage, the amount being raised in US dollars, and a one-paragraph problem statement. Use when: only when a founder explicitly asks to create a draft of their own pitch and has given you a PitchSpark submit token (pss_...). Do not use for: investors; searching or reading pitches (use pitchspark_search_pitches_v1 and pitchspark_get_pitch_v1); anything the founder has not explicitly asked for. Requires a PitchSpark submit token: the founder generates one in PitchSpark Settings (Submit tokens), copies it once and gives it to the assistant, which sends it as the header "Authorization: Bearer pss_...". A submit token works only for this tool and only creates drafts; it expires 30 days after it is created and the founder can revoke it in Settings at any time. PitchSpark API keys (psk_...) and sign-in session tokens are refused, and there are no anonymous submissions. The draft is not listed, searchable (through this server or on PitchSpark) or scored until the founder completes it and submits it for review in Pitch Studio, at the edit_url returned. One call creates at most one pitch, subject to the account's pitch limit; a company the founder already has a pitch for is refused rather than listed twice. Nothing else changes: no score, feedback or existing pitch is touched and no email is sent. The tagline is the first sentence of the problem statement (at most 100 characters); the founder can change it in Pitch Studio. Returns {"pitch_id","status":"draft","company_name","edit_url"}. Limits: 5 submissions per account per hour, and 30 tool calls per minute per connection. Errors are JSON {"error":{"code","message","retry_after_seconds"}}: UNAUTHORIZED (no submit token, or one that is unknown, revoked or expired, or an API key or session token was sent instead; the message says how to get a submit token and how to sign up at pitchspark.io), INVALID_ARGUMENT, CONFLICT (the founder already has a pitch for this company), PITCH_LIMIT_REACHED (the account's pitch limit is reached), RATE_LIMITED (with retry_after_seconds), INTERNAL. Calls are logged without the company name, the problem statement or the token.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company_name": "<company_name>",
      "sector": "<sector>",
      "stage": "<stage>",
      "raise_amount_usd": "<raise_amount_usd>",
      "problem_statement": "<problem_statement>"
    },
    "name": "pitchspark_submit_pitch_v1"
  }
}

Input Schema

NameRequiredDescriptionDefault
stageYesThe funding stage of the round being raised. One of: pre_seed, seed, series_a, series_b, series_c, bridge_mezzanine, growth, acquisition. Example: "seed".
sectorYesThe startup's primary sector. One of: fintech, healthtech, saas, marketplace, ai_ml, consumer, enterprise, climate, edtech, crypto, biotech, hardware, gaming, real_estate, food_beverage, fashion, travel, sports, media, femtech, cybersecurity, dev_tools, ecommerce, logistics, mobility, hr_tech, legal_tech, insurtech, proptech, agtech, energy, robotics, govtech, hospitality, other. Common names like "AI", "climate tech" or "web3" are accepted, as in search; anything else is rejected. Example: "fintech".
company_nameYesThe startup's name, 1 to 120 characters on one line, e.g. "Acme Robotics".
raise_amount_usdYesThe amount being raised in this round, in US dollars: more than 0, at most 10000000000. Example: 1500000 for $1.5M.
problem_statementYesOne paragraph, 40 to 1200 characters, on the problem the startup solves and for whom. No blank lines: a single line break is joined into a space, a second paragraph is rejected. Its first sentence becomes the pitch's tagline.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent only when the call failed (isError true).
statusNo
edit_urlNo
pitch_idNo
company_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "anyOf": [
      +    {
      +      "required": [
      +        "pitch_id",
      +        "status",
      +        "company_name",
      +        "edit_url"
      +      ]
      +    },
      +    {
      +      "required": [
      +        "error"
      +      ]
      +    }
      +  ],
      +  "properties": {
      +    "company_name": {
      +      "type": "string"
      +    },
      +    "edit_url": {
      +      "type": "string"
      +    },
      +    "error": {
      +      "additionalProperties": false,
      +      "description": "Present only when the call failed (isError true).",
      +      "properties": {
      +        "category": {
      +          "description": "The error class.",
      +          "enum": [
      +            "RATE_LIMITED",
      +            "QUOTA_EXCEEDED",
      +            "UNAUTHORIZED",
      +            "FORBIDDEN",
      +            "VALIDATION_ERROR",
      +            "NOT_FOUND",
      +            "CONFLICT",
      +            "UNKNOWN_TOOL",
      +            "INTERNAL"
      +          ],
      +          "type": "string"
      +        },
      +        "code": {
      +          "description": "Machine-readable error code, e.g. RATE_LIMITED, UNAUTHORIZED, FORBIDDEN, INVALID_ARGUMENT, NOT_FOUND, CONFLICT, PITCH_LIMIT_REACHED, INTERNAL.",
      +          "type": "string"
      +        },
      +        "message": {
      +          "description": "A short human-readable explanation, safe to show the user. Never a stack trace.",
      +          "type": "string"
      +        },
      +        "retry_after_seconds": {
      +          "description": "Seconds to wait before retrying, when waiting helps.",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "retryable": {
      +          "description": "true when the same call can succeed later without changes.",
      +          "type": "boolean"
      +        }
      +      },
      +      "required": [
      +        "code",
      +        "message"
      +      ],
      +      "type": "object"
      +    },
      +    "pitch_id": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "enum": [
      +        "draft"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true); the description goes far beyond by explaining token scope, 30-day expiry, revocation, refusal of psk_/session tokens, draft invisibility until review, one-pitch-per-company conflict behavior, rate limits, error codes, and log redaction. This is exactly the context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with purpose, then usage, then auth, then side effects, then return/limits/errors — a logical progression with no filler sentences. It is dense and long, but nearly every clause carries operational information; a slightly tighter grouping of limits and errors would improve scanability.

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

Completeness5/5

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

For a mutating, token-authenticated, rate-limited creation tool, the description covers auth acquisition, side effects, idempotency-adjacent conflict behavior, return shape, and the full error taxonomy. Even though an output schema exists, the inline return summary and error codes make the definition self-sufficient.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds a rule not present in the schema: the tagline is derived from the first sentence of the problem statement (max 100 chars) and is editable later. It also frames the five required facts as a set, though it does not add per-parameter format detail beyond the schema.

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

Purpose5/5

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

States a specific verb and resource ('create a DRAFT startup pitch on the signed-in founder's own PitchSpark account') and enumerates the five input facts. It explicitly distinguishes itself from the read-oriented siblings pitchspark_search_pitches_v1 and pitchspark_get_pitch_v1, so an agent can route correctly without opening a schema.

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

Usage Guidelines5/5

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

Provides an explicit 'Use when' clause (founder explicitly asks for a draft of their own pitch and supplies a pss_ token) and a 'Do not use for' clause naming investors, searching/reading pitches, and unrequested actions. Alternatives are named directly, leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources