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

Annotations already cover readOnly/idempotent/non-destructive, so the description's added value is the reply ordering ('newest first') and the payload warning ('with messages'), which signals the results can be heavy. That is real behavioral context beyond structured fields, though there is no mention of pagination or limits.

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?

Two tightly written sentences with zero filler, and the core capability plus result ordering are front-loaded before the source disambiguation. Dense but not bloated; no sentence could be dropped without losing information.

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 a read-only, no-required-parameter list tool with no output schema, the description covers sources, ordering, and filtering well enough to invoke correctly. The only gap is any indication of result size or limits, which matters given the 'with messages' payload.

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 60% (enums for scope and source are present but the ID fields only say 'Document id' etc.). The description compensates by explaining what the 'source' enum values actually mean and by tying each ID filter to a resource, which the schema does not. The 'scope' enum values themselves (GENERAL, DOCUMENT, etc.) are left uninterpreted.

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 ('List the user's AI chat threads'), adds ordering and payload shape ('newest first, with messages'), and disambiguates the two data sources. An agent can tell this apart from get_chat_thread (single thread) and from unrelated list_* siblings without opening a schema.

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 explains when each source applies: 'brain' is the study-assistant chat that ask_brain writes to, while 'copilot' lists in-app copilot conversations. It also tells the agent the filtering axes (scope, or the document/lecture/flashcard set a chat is about). It stops short of naming a specific alternative tool or stating exclusions, so not a 5.

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