Skip to main content
Glama

Count the development pipeline

count_pipeline
Read-onlyIdempotent

Use this when the user asks how many drug and therapy programs there are, or how a field's pipeline splits. Counts programs by stage, modality, target, hallmark, indication, the developer's country or the developer, each group by stage. Takes list_assets' filters: by=target with indication=obesity counts the targets of obesity programs. A plan that includes drug and therapy programs reads every record in full; others read an outline, as on the site.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "count_pipeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoLetters and digits in any of the asset's names or code names (`UBX1325` matches UBX-1325).
byNoWhat to group by.stage
kindNo`any` for all; counts default to program.
limitNoResults per page.
stageNoStage: with `indication`, the stage for that indication; otherwise the asset's furthest stage. `discontinued` takes programs whose development status is discontinued, whatever stage they reached; a phase leaves them out.
targetNoA target: a gene symbol or key (`GLP1R`, `bcl2l1`) or a process key (`mtor`, `cellular-senescence`).
countryNoThe developer's country, ISO 3166 alpha-2 (`US`, `GB`, `CH`).
hallmarkNoA hallmark of aging the asset acts on.
modalityNoThe kind of therapy (see `modality`).
mechanismNoWords that must all appear in the asset's mechanism line (case-insensitive).
indicationNoA disease, by name or entity key (`idiopathic pulmonary fibrosis`, `alzheimer-disease`).
organisationNoAn organization key: the assets it develops, partners on or licensed out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / stage / description
      Previous value: -"Stage: with `indication`, the stage for that indication; otherwise the asset's furthest stage."New value: +"Stage: with `indication`, the stage for that indication; otherwise the asset's furthest stage. `discontinued` takes programs whose development status is discontinued, whatever stage they reached; a phase leaves them out."
  2. Changed1 schema field changed
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "`any` for all; counts default to program.",
      +  "enum": [
      +    "program",
      +    "repurposing",
      +    "research",
      +    "any"
      +  ],
      +  "type": "string"
      +}
  3. Changed5 schema fields changed
    • removedInput schema / properties / by / examples
      Removed value: -[
      -  "modality"
      -]
    • removedInput schema / properties / hallmark / examples
      Removed value: -[
      -  "cellular-senescence"
      -]
    • changedInput schema / properties / limit / description
      Previous value: -"Results per page, 1 to 25."New value: +"Results per page."
    • removedInput schema / properties / modality / examples
      Removed value: -[
      -  "small_molecule"
      -]
    • removedInput schema / properties / stage / examples
      Removed value: -[
      -  "phase2"
      -]
  4. Changed1 schema field changed
    • changedInput schema / properties / organisation / description
      Previous value: -"An organisation key: the assets it develops, partners on or licensed out."New value: +"An organization key: the assets it develops, partners on or licensed out."
  5. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds the notable behavior that the returned detail depends on the plan ("a plan that includes drug and therapy programs reads every record in full; others read an outline"), which is real context an agent cannot get from structured fields. It does not mention pagination behavior despite a limit default of 10 and max of 25, and that plan sentence is vague enough to be hard to act on.

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?

Four sentences, front-loaded with the when-to-use condition followed by the grouping axes, then filter semantics, then the plan caveat. Every sentence carries content, though the closing plan sentence is jargon-heavy and would be clearer as a direct statement about result completeness.

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?

For a 12-parameter, zero-required aggregation tool with no output schema, the description covers the counting axes, filter inheritance and result-depth caveat. What an agent would still want — the shape of the count response and how paging works — is not covered, but the essentials for correct invocation are present.

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 coverage is 100%, so the schema already documents all 12 parameters including enums, defaults and examples. The description adds one genuinely useful semantic point — that filters restrict the counted population ("by=target with indication=obesity counts the targets of obesity programs") — but nothing about the interaction of stage with indication beyond what the schema's own stage description already states.

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 (counts) and resource (drug and therapy programs), plus the exact grouping axes: stage, modality, target, hallmark, indication, country, developer. It is immediately distinguishable from list_assets, which returns records rather than tallies.

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

Usage Guidelines4/5

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

"Use this when the user asks how many drug and therapy programs there are, or how a field's pipeline splits" gives a clear triggering condition, and "Takes list_assets' filters" anchors it to the sibling's filter vocabulary. It never explicitly says to use list_assets when the user wants the underlying records instead of counts, so the routing is implied rather than spelled out.

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.