request_client_accessFor an AGENCY: email one of its clients asking them to let the agency see their account health, read-only. The email explains what the agency would and would never see, and links to the owner's switch. Sends a real email — confirm with the agency first. At most once every three days per client.
| Name | Required | Description | Default |
|---|---|---|---|
| client | Yes | The client's name as shown in my_agency. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing that it sends a real email, the email's content (what the agency would and would never see, plus a link to the owner's switch), a confirmation requirement, and a rate limit of once every three days per client. The rate limit and irreversible-send nature are exactly the context annotations cannot express.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, front-loaded with the 'For an AGENCY' scope, then behavior, confirmation, and rate limit. Efficient and each clause earns its place, though the switch/email-content detail runs slightly long for a one-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is needed since the tool's effect is an outbound email and the description covers outcome, confirmation, and cadence limits. Nothing an agent needs to invoke it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both the schema description ('The client's name as shown in my_agency') and coverage (100%) already document the sole parameter. The description adds no format, lookup, or disambiguation detail beyond what the schema provides, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource (email a client to request read-only account access) and scopes it to an AGENCY, cleanly distinguishing it from siblings like invite_client_to_shearquery and find_client. An agent can identify the action without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'For an AGENCY' sets the caller context and 'confirm with the agency first' gives an explicit pre-condition. However, it never names or contrasts a sibling (e.g., invite_client_to_shearquery) or states when access should already exist, so the alternative-selection guidance is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.