read

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: stateful defaults (new since your last read, first run last 24h, newest message per chat) and that full=true changes result scope, which an agent cannot infer from the schema or annotations.

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?

It is extremely compact and front-loads the purpose before the argument-driven modes, with zero filler sentences. The telegraphic fragments ('chats: latest.', 'refs: around citations') are dense but readable, so nothing is wasted.

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?

For an 11-parameter tool with 9% schema coverage and no output schema, the description covers the default behavior and four major modes but omits four parameters and any sense of return shape or result limits. Adequate for common paths, incomplete for the full parameter surface.

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 description coverage is only 9%, so the description carries most of the burden and it does explain chats, since/until, refs, before/after, and full. However 'from', 'limit', 'media' (an enum filter), and 'budget' receive no semantic explanation anywhere, leaving a meaningful 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?

The opening 'Read messages in order' gives a specific verb plus resource, so the agent knows this retrieves messages rather than searching, exporting, or aggregating. It does not name or differentiate from the sibling 'search' tool, so it stops short of the 5 tier.

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 lays out explicit invocation modes keyed to arguments: no args means new-since-last-read, 'chats' means latest, 'since/until' means a period, 'refs' means around citations. That is strong conditional guidance, but it never states when to prefer this over 'search' or 'export', so no exclusions are given.

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