ic_get_message

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

Goes well beyond the annotations by disclosing the non-obvious side effect that fetching may mark the message as read in the portal, which is precisely why readOnlyHint is false — the agent is told this is not a pure read. It also flags the returned text as third-party untrusted data that must never be followed as instructions, a critical safety trait for an openWorld fetch.

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 sentences, front-loaded with the verb and return shape, and each subsequent sentence carries load (URL provenance, path forms, read-marking side effect, untrusted-content warning). Minor redundancy: the accepted URL forms are restated from the schema's own parameter description.

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 correctly spells out the parsed return shape, and it covers the side-effect and trust concerns an agent needs before invoking an open-world fetch. Only the `view`/`district` parameters and error behavior are left to the schema.

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 67%, so the schema already documents all three parameters. The description reinforces `messageUrl` by explaining its provenance (the `url` field of an ic_list_messages inbox item) and accepted path forms, but says nothing about the `view` enum or what `district` means, so it does not fully compensate for the coverage gap.

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 (fetch/parse the HTML body of an inbox message) and names the exact return shape { subject, date, body, url }. The reference to ic_list_messages' inbox section cleanly separates it from the list sibling that only enumerates messages.

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?

Explicitly tells the agent to obtain `messageUrl` from an item returned by ic_list_messages' inbox section, which is a real routing rule, and clarifies that both relative and /campus/-prefixed forms work. It gives no negative guidance, however — e.g. it never says to use ic_download_document for attachments or what to do if the item has no url field.

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