Skip to main content
Glama

PitchSpark: Pre-Seed & Seed Deal Flow

Compare 2 to 4 startup pitches side by side: scores, traction, raise and decisions

pitchspark_compare_pitches_v1
Read-onlyIdempotent

Compare 2 to 4 pitches side by side: ask, stage, sector, HQ region, traction note, green flags, public score, dimension scores (keyed callers, public scores only) and compact decision aggregates (likes vs passes, average rating, top pass reasons; investor API keys only, else reason key_required; each withheld below 5 distinct signed-in users, counts as bands; the likes-vs-passes block may be withheld with reason hidden_pending_review, and the team-related pass reasons are withheld pending review). Use when: an investor is choosing between shortlisted pitches. Do not use for: more than 4 pitches (run pitchspark_search_pitches_v2 sorted by score instead), full pitch text (pitchspark_get_pitch_v2). All ids must be distinct and resolvable: any id that is missing, not public or opted out answers NOT_FOUND for the whole call, and nothing is counted. The whole comparison is delivered or nothing is (a spent allowance answers RATE_LIMITED). Returns {"pitches":[...in the order given], "attribution"}. Each pitch this tool returns counts 1 against the daily pitch allowance (the same allowance as pitchspark_search_pitches_v1), or 0 when the same API key (without a key, the same connection) already got that pitch today. Calls are logged, and each pitch returned is counted as a view.

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": {
      "ids": "<ids>"
    },
    "name": "pitchspark_compare_pitches_v1"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYes2 to 4 distinct pitch ids.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent only when the call failed (isError true).
pitchesNo
attributionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so this is credit for the additional disclosure: atomic fail-or-nothing resolution (one bad/private/opted-out id returns NOT_FOUND for the whole call and nothing is counted), RATE_LIMITED on a spent allowance, per-pitch allowance accounting with a same-key dedupe exception, and view logging. It also discloses partial-data behavior in detail — decision aggregates gated on an investor API key (else key_required), suppression below 5 distinct signed-in users with counts returned as bands, and pending-review withholding for the likes-vs-passes block and team pass reasons.

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

Conciseness3/5

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

The opening sentence is a single run-on that crams a ten-item field list plus four separate parenthetical withholding rules into one breath, making it hard to scan. Every fact is load-bearing, but the dense inline parentheses and repeated 'withheld' clauses would be far clearer as a short bulleted list of return fields and their gating conditions.

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 single-parameter read tool with an output schema, the description covers everything an agent needs to call it correctly and interpret failure: input validity, ordering guarantee, error codes, rate-limit accounting, and why individual fields may be missing. Nothing material is left to inference despite the complexity of the suppression rules.

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 pattern, minItems/maxItems and uniqueItems rules are already documented. The description still adds real meaning the schema cannot express: ids must be resolvable and public, an unresolvable id fails the entire call, and results come back 'in the order given'. It does not explain what an id looks like beyond 'the pitch id from a search result', which the schema handles.

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?

Opens with a specific verb, resource and explicit scope: 'Compare 2 to 4 pitches side by side', then enumerates exactly which fields are compared (ask, stage, sector, HQ region, traction, scores, decision aggregates). The 'Do not use for' clause names pitchspark_search_pitches_v2 and pitchspark_get_pitch_v2, so an agent can separate this from its siblings without opening any 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?

Gives an explicit trigger ('an investor is choosing between shortlisted pitches') and two explicit exclusions with the correct alternative for each: more than 4 pitches -> search_pitches_v2 sorted by score, full pitch text -> get_pitch_v2. The 2-to-4 limit is restated as a routing condition rather than left as a schema constraint.

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