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

Annotations already declare a safe read, but the description adds substantive behavior: Instagram serves only recent history (~20 messages, no older ones), long messages are truncated, and the content is private and must be reported only to the account owner. That is real context beyond the annotations, though nothing is said about whether the returned order interacts with the limit window.

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?

Front-loaded with what is returned, then usage, then identifier plumbing, then behavioral caveats and the privacy warning. Four dense sentences; the privacy sentence is arguably a slight expansion but it is operationally load-bearing, so nearly every sentence earns its place.

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?

With no output schema, the description does the job of describing the return shape (messages with sender and timestamp) and the truncation/recency limits. Missing nothing critical for calling it, though a note on pagination or what happens if the threadId is stale would fully close the loop.

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?

Schema coverage is 100%, so every parameter (including the 50-cap on limit and the default account fallback) is already documented in the schema. The description only reinforces the threadId sourcing, adding no new semantics. 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 ('The messages of one Instagram direct message conversation') plus return shape ('oldest first, each with who sent it and when'). This is clearly distinct from inbox_conversations (list threads) and inbox_send_reply (write), so an agent can route without opening schemas.

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?

Names the sequencing ('Use it after inbox_conversations') and the triggering intents ('what a particular person said, what was already answered, or wants help drafting a reply'). It also tells the agent where the required identifier comes from, which is explicit when-to-use guidance.

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