read_the_messagesReturns every message with who left it and what they said. A written message reads back whatever was paid; a voice or a video is written out on the tier that includes the words, and where it is not, the tool says so rather than half-answering.
| Name | Required | Description | Default |
|---|---|---|---|
| book | Yes | The handle start_book gave you. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotent, so the safety profile is covered. The description adds real behavioral context by explaining how voice or video messages are handled (only written out when the tier includes them) and explicitly states the tool refuses to half-answer rather than giving partial results. This goes beyond the annotations and helps an agent predict edge-case behavior.
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 only two sentences and leads with the main action. The second sentence, while a bit dense, conveys important edge cases about voice/video handling without unnecessary words. It earned its place and stays compact, though the semicolon-comma flow could be smoother.
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?
Although there is no output schema, the description states the shape of the return value: every message with who left it and what they said. The necessary parameter is documented in the schema, and the description handles the voice/video tier case. I am missing, maybe, ordering or pagination details, but the tool is simple enough that this is not fatal.
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 schema description for 'book' ('The handle start_book gave you') already defines what the parameter is, and coverage is 100%, so the baseline is 3. The tool description does not add any additional semantics about the parameter beyond what the schema already provides.
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 opens with 'Returns every message with who left it and what they said,' which states the exact verb (returns), resource (messages), and what data is included (who left it, content). It distinguishes clearly from sibling tools like book_status or find_book, so an agent immediately understands this is the message-reader tool.
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?
The description implies that the tool is used when you want to retrieve messages, but it gives no explicit context for when to use it versus alternatives, nor any exclusions or prerequisites. There is no mention of 'use this instead of X if you need Y.' The usage is inferable but not stated.
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.