Skip to main content
Glama

Edit company profile

editCompanyProfile
Destructive

Update the company profile or record notes about the company. update: writes the fields you pass. Omitted fields are left untouched. The four long-text fields (description, descriptionShort, about, culture) are written only when they are currently blank, so an existing value is never overwritten by default; every other field overwrites unconditionally. With overwrite=true it also replaces already-filled long-text fields; pass overwrite only when the user explicitly asks to replace or rewrite an existing value. update_memory: memoryUpdates. Records company-wide notes per topic key (hiring_process, company_culture, communication_preferences, compensation_patterns, deal_breakers): how they hire, what they consistently reject, how they like to be updated. Record a note the moment the contact tells you something durable, without being asked. A null value deletes the key; reuse an existing key instead of adding a near duplicate. Notes about one role go to the job tool's update_memory command. Every note refreshes the hiring rubric Clera uses to pick candidates for this company. Always run readCompanyProfile get before update so you do not resend values that are already set.

Clera privately records this tool's inputs and results for usage tracking and support.

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": {
      "command": "<command>"
    },
    "name": "editCompanyProfile"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoupdate: company name, replaces the placeholder name after scraping
aboutNoupdate: longer about section (written only when blank)
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
commandYesWhich operation to run: update | update_memory. The tool description explains each.
cultureNoupdate: company culture values as a list (written only when blank)
logoUrlNoupdate: company logo URL
benefitsNoupdate: employee benefits as a list
industryNoupdate: industry
overwriteNoupdate: set true ONLY when the user explicitly asks to replace an existing narrative value (description, descriptionShort, about, culture); it makes those fields overwrite instead of fill-when-blank
teamAboutNoupdate: about the team, who they are, backgrounds
techStackNoupdate: technology stack as a list
websiteUrlNoupdate: company website URL
companySizeNoupdate: current team size (e.g. '11-50')
descriptionNoupdate: company description / elevator pitch (written only when blank)
foundedYearNoupdate: year the company was founded
linkedinUrlNoupdate: company LinkedIn URL
fundingStageNoupdate: funding stage (seed, series-a, etc.)
fundingAmountNoupdate: total funding raised (e.g. '$3.8M')
memoryUpdatesNoupdate_memory (required): notes to upsert, a null value deletes the key
officeLocationsNoupdate: office locations as a list (e.g. ['San Francisco, CA', 'Remote'])
descriptionShortNoupdate: one line company description (written only when blank)
lastFundingRoundNoupdate: most recent funding round (e.g. 'Series A')
productDescriptionNoupdate: what the company's product does

Output Schema

NameRequiredDescriptionDefault
commandYes
entriesNo
profileYes
diffBlockNo
memorySavedNo
fieldsUpdatedNo
memoryRemovedNo
skippedNarrativeNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, idempotentHint=false), the description discloses the exact mutation model: omitted fields are untouched, the four long-text fields are fill-when-blank only, every other field overwrites unconditionally, null deletes a memory key, and near-duplicate keys should be reused. It also notes that input/results are recorded for usage tracking, a behavioral fact not present in any structured field.

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?

It is front-loaded with the two commands and uses a consistent update:/update_memory: structure that makes scanning easy. A few lines are tax: the topic-key list restates the schema enum, and the trailing privacy notice is boilerplate, but the density is reasonable for a 23-parameter tool.

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 multi-command mutation tool with 23 parameters, the description covers command selection, write semantics, safety conditions, prerequisite reads, and note-recording policy, and an output schema already documents return values. Nothing an agent needs in order to call it correctly is missing.

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?

With schema coverage at 100% the baseline is 3, and the description earns a bump by explaining semantics the schema only partially conveys: which four long-text fields share fill-when-blank behavior, that overwrite modifies that behavior rather than acting as a general replace flag, and that a null memory value deletes the key. It stops short of clarifying the orgId or command interaction beyond one line.

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 opens with a specific verb and resource ('Update the company profile or record notes about the company') and then splits the tool into its two named commands, update and update_memory, spelling out what each does. An agent can tell it apart from siblings such as readCompanyProfile and from editJob's own update_memory command without opening either 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?

It gives explicit when-to-use rules: pass overwrite ONLY when the user explicitly asks to replace or rewrite an existing value, record a note the moment the contact says something durable, and route notes about a single role to the job tool's update_memory instead. It also imposes a prerequisite workflow ('Always run readCompanyProfile get before update'), which is the strongest kind of guidance.

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