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

The description states 'Marks it read,' which is an explicit state mutation, while the annotations declare readOnlyHint=true (does not modify its environment). This is a direct contradiction. It also omits how errors, large conversations, or repeated reads interact with that side effect.

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-loads the core action, then layers paging, side-effect, and routing instructions in compact sentences. Slightly dense (four distinct ideas packed in three sentences) but no wasted prose.

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 an output schema covering return values and annotations covering the safety profile, the description supplies the paging mechanic and flag routing, which is useful. It still leaves the sibling-selection question and the exact consequences of the read-receipt side effect unresolved.

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 50% (conversationId is undocumented, `before` is documented). The description adds real meaning by explaining `before` as the olderCursor used to page back and by specifying oldest→newest ordering, but does not expand on conversationId. Baseline 3 is appropriate.

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 and resource — 'Read messages in one conversation' — and adds scope detail ('oldest→newest'). It is clearly differentiated from list-oriented siblings like list_conversations and read_unread by operating on messages within a single conversation, though it never names a sibling explicitly.

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?

Gives conditional routing to one alternative ('if anything matches the flag list in relay_status rules, call flag_conversation') and usage guidance for paging ('pass before = olderCursor'). However it never says when to choose this over read_unread, pro_conversations, or list_conversations, so sibling selection is left mostly to inference.

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