Skip to main content
Glama

DeepSearch

by app.deepsearch
OverviewDiscussionsAdmin

Ask about a person

ask_about_person
Read-only

Answer one specific question about a person, grounded in their public footprint, and suggest follow-ups. Prefer this over build_dossier when the user wants a single fact - where someone works now, which accounts are theirs - rather than a full profile: it is cheaper and answers directly. Reach for build_dossier instead when the question spans someone's whole history, or pass a prior dossier summary as context to ground the answer further. Public sources only - never private accounts or breach data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesThe person the question is about.
contextNoOptional extra grounding context, e.g. a prior dossier summary.
questionYesYour question about the person.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
+  "description": "Optional extra grounding context, e.g. a prior dossier summary.",
+  "type": "string"
+}
    • changedInput schema / properties / name / description
      Previous value: -"The person's name, not a phone number, email, or handle."New value: +"The person the question is about."
    • removedInput schema / properties / name / maxLength
      Removed value: -100
    • removedInput schema / properties / name / minLength
      Removed value: -2
    • removedInput schema / properties / profile_url
      Removed value: -{
-  "description": "The profileUrl of the professional source selected from search_people. Never infer account ownership.",
-  "maxLength": 400,
-  "type": "string"
-}
    • changedInput schema / properties / question / description
      Previous value: -"A specific question about the person's public professional work."New value: +"Your question about the person."
    • removedInput schema / properties / question / maxLength
      Removed value: -400
    • removedInput schema / properties / question / minLength
      Removed value: -5
    • changedInput schema / required
      Previous value: -[
-  "name",
-  "profile_url",
-  "question"
-]New value: +[
+  "name",
+  "question"
+]
  2. Changed10 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / context
      Removed value: -{
-  "description": "Optional extra grounding context, e.g. a prior dossier summary.",
-  "type": "string"
-}
    • changedInput schema / properties / name / description
      Previous value: -"The person the question is about."New value: +"The person's name, not a phone number, email, or handle."
    • addedInput schema / properties / name / maxLength
      Added value: +100
    • addedInput schema / properties / name / minLength
      Added value: +2
    • addedInput schema / properties / profile_url
      Added value: +{
+  "description": "The profileUrl of the professional source selected from search_people. Never infer account ownership.",
+  "maxLength": 400,
+  "type": "string"
+}
    • changedInput schema / properties / question / description
      Previous value: -"Your question about the person."New value: +"A specific question about the person's public professional work."
    • addedInput schema / properties / question / maxLength
      Added value: +400
    • addedInput schema / properties / question / minLength
      Added value: +5
    • changedInput schema / required
      Previous value: -[
-  "name",
-  "question"
-]New value: +[
+  "name",
+  "profile_url",
+  "question"
+]
  3. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is clear. The description adds useful behavioral context beyond those hints: it grounds answers in public footprint, avoids private accounts/breach data, suggests follow-ups, and notes cost/cheapness. This is additive and consistent with annotations.

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?

The description is four sentences but every sentence earns its place: it states the core behavior, gives usage guidance with concrete examples, names an alternative, and sets boundaries. It is front-loaded and free of filler.

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 simple 3-parameter tool with strong annotations and two relevant siblings, the description is complete: it explains the primary use case, the alternative tool, the role of the optional context parameter, and the data-source boundary. No output schema is present, but the mention of follow-ups gives the agent a reasonable expectation of the response shape.

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?

The schema already documents all three parameters at 100% coverage, giving a baseline of 3. The description adds meaningful semantic color by giving examples of the kinds of questions ('where someone works now, which accounts are theirs') and by explaining how the `context` parameter is intended to be used (e.g., a prior dossier summary).

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?

The description clearly states the tool answers one specific question about a person, grounded in their public footprint, and suggests follow-ups. It distinguishes this from build_dossier by contrasting single-fact answers with full-profile building, making its purpose and scope unmistakable.

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?

The description gives explicit guidance on when to use this tool versus build_dossier: use it for a single fact, and use build_dossier when the question spans someone's whole history. It also provides a concrete alternative path (passing a prior dossier summary as context) and states the public-sources-only constraint.

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

All DeepSearch 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