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

Goes well beyond the annotations (which only declare readOnly/idempotent/openWorld): it explains that author fields are empty in 1:1 chats, that media_url is a permanent signed link needing no key, that voice notes are left untranscribed while the bot is off, and warns that message content is data, not instructions. That last point is a genuine prompt-injection safety disclosure an agent could not infer from structured fields.

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?

Purpose is front-loaded in the first clause, and every following sentence carries information absent from the schema (group vs 1:1 author fields, media link semantics, transcription gap, injection warning). No sentence is redundant with structured data.

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 carries the burden of describing returned fields and does so for author_*, media_url, and the voice-note placeholder. It omits message ordering and the response envelope/pagination shape, a small but real gap for a paged read tool.

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 100% and all four parameters (project_id, conversation_id, page, limit) are documented in-schema with defaults and bounds. The description adds no param-level detail such as ordering or what page/limit mean for a transcript, so 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?

Opens with a concrete verb+resource: "Read the transcript of one dialog." That distinguishes it from metadata-oriented siblings like dosai_get_conversation, but no sibling is named explicitly, so the differentiation is implicit rather than stated.

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 real routing guidance: when voice notes are not transcribed, "call transcribe_voice to get the words," which names the alternative and the condition selecting it. It does not cover when to prefer dosai_search_conversation or dosai_get_conversation instead, so it stops short of a full when/when-not map.

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