Skip to main content
Glama
agentisend

agentisend

Who am I and what may I do?

whoami
Read-onlyIdempotent

Check your account identity, permissions, budgets, sending capacity, and current send status before taking action or after a refusal; this read-only tool changes nothing.

Instructions

Purpose: the one read to make before deciding anything, and again after any refusal. Answers who you are and what you may do. NOT for: changing anything. Returns: the account and key, the scopes held, the tools those scopes can call, budget consumed and remaining with its refill time, the per-minute ceilings, whether the kill switch is down, the account trust standing, can_send_now as the summary for real recipients, can_send_to_simulator for test sends to @simulator.agentisend.com addresses, capacity.per_mail_system_per_hour (this account's own cap for one receiving mail system; 10 until the account is 7 days old) and capacity.shared_pool_per_mail_system_per_hour (all customers together), pending_approvals: sends from this key waiting for a person, which hold only those sends, test_send: before a domain verifies, the address a first test goes from and the account's own addresses it can go to, sending_domains.limit: how many verified sending domains this plan may hold (null when the plan has no cap), and next_step: when this account has no domain, one sentence telling you to offer setup plus the tools create_domain, get_domain and wait_for_domain (null once a domain exists).

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": "whoami"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
trustNo
budgetNo
scopesNo
capacityNoHow fast mail can leave today.
next_stepNoSet when this account has no domain. Null once a domain exists.
test_sendNoWhere a first test can go before a domain verifies, or null.
account_idNoIdentifier.
api_key_idNoIdentifier.
loop_guardNoHow this key watches sends. repetition-only (the default) holds near-identical repeats. full also holds a send to an inbox the last hour collapsed onto. off holds nothing. A marketing send on a key with no setting still uses full.
kill_switchNo
api_key_nameNo
can_send_nowNoTrue when a real recipient would be accepted.
callable_toolsNo
quota_resets_atNoISO 8601 time.
sending_domainsNoThe domain cap create_domain enforces for this account.
pending_approvalsNo
can_send_to_simulatorNoTrue when an address ending in @simulator.agentisend.com would be accepted.
rate_limits_per_minuteNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes well beyond that, disclosing the kill switch, budget refill timing, trust standing, per-mail-system caps with the 10-until-7-days-old rule, and the fact that pending_approvals only hold those specific sends — genuinely useful operational context.

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

Conciseness2/5

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

Purpose and exclusion are front-loaded and clearly labelled, but the 'Returns' portion is one enormous run-on sentence enumerating roughly fifteen fields, most of which an output schema already documents. That bulk does not earn its place and makes the definition hard to scan.

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 zero-parameter read with full annotation coverage and an output schema, the description is more than complete — it even covers null semantics for next_step and sending_domains.limit. The only shortfall is the absence of routing against sibling reads that overlap its output.

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 tool takes no parameters, so the baseline is 4 and there is nothing further the description could add. No parameter semantics are missing.

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: a self-inspection read that answers who the caller is and what it may do. The framing 'the one read to make before deciding anything' sharply distinguishes it from the mutating siblings in the catalog.

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?

Gives explicit timing guidance ('before deciding anything, and again after any refusal') and an explicit exclusion ('NOT for: changing anything'). It does not, however, distinguish itself from siblings that return overlapping subsets such as get_agent_budget, get_trust_standing, get_kill_switch_state or list_pending_approvals, so an agent cannot tell when the narrower read suffices.

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