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

Annotations already establish a safe, idempotent read, but the description adds substantial non-structured behavior: message bodies are capped, media is metadata-only with specific fields, transcripts need another tool/scope, group messages conditionally include sender_phone/sender_contact_name/sender_hidden/sender_key, and sender_key is explicitly non-reversible. It also flags message text as untrusted customer-authored content, which is important safety context an agent cannot get from 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?

Front-loaded with the primary behavior and pagination, then grouped by concern (anchoring, media, group sender fields, trust warning). It is a dense single paragraph; the sender_key explanation is verbose, but each clause conveys functional or safety information rather than filler.

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?

An output schema exists, so return shape need not be spelled out, and the description correctly spends its words on pagination direction, anchor behavior, scope-gated fields, media limitations, and the untrusted-content caveat. For a 4-parameter read tool with conditional enrichment and side tools required, this covers everything an agent needs to call it correctly.

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 0%, so the description must carry parameter meaning, and it does for the two hardest ones: anchor_message_id gets a concrete use case and window semantics, and the 'cursor' parameter is described via its returned next_cursor. However, 'limit' (1-50) is never explained and the description uses 'next_cursor' while the schema names the param 'cursor', leaving a small naming inference 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?

Opens with a precise verb+resource+scope: 'Message history for one conversation, newest first'. It is immediately distinguishable from search_messages_and_contacts (cross-conversation search) and get_chat_summary (summaries), both of which are named or implied as different tools.

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 routes the agent: normal paging uses next_cursor, while anchor_message_id is for fetching a window around a known message (with the example of an evidence source from get_chat_summary). It also states the alternative for media ('require the get_media tool and the read_media scope') and the scope conditions for group sender enrichment.

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