Pilot MCP

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It fails to specify how many messages are returned (recent N? all?), the sort order, whether the conversation is persisted as 'read', or how the target conversation is determined without input parameters. Only conveys that it is a read operation.

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?

The description is extremely concise at only 5 words, but this brevity crosses into under-specification given the ambiguity around how the tool identifies which conversation to read without parameters. No structural issues, but content is insufficient for the complexity implied.

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?

Given that reading messages typically requires specifying a conversation/thread and the schema provides no parameters, the description is critically incomplete. It fails to explain the implicit selection logic or output format, leaving an agent unable to predict what will be returned or from where.

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?

The input schema contains zero parameters, which per the evaluation rules establishes a baseline of 4. The description neither adds nor subtracts value regarding parameters since none exist to describe, though it notably fails to explain the absence of parameters (e.g., implicit context usage).

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?

The description states the basic action (read messages) and source (conversation), but is vague regarding which messaging platform (iMessage, Teams, generic?) and fails to differentiate from siblings like 'search_messages' or 'teams_read_chat_messages'. It leaves the critical question of 'which conversation' unanswered given the parameter-less 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?

Provides no guidance on when to use this tool versus alternatives like 'search_messages' (which supports filtering), 'teams_read_chat_messages', or 'read_email'. Does not explain the prerequisite of how a conversation is selected when no parameters are provided.

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