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

With no annotations, the description carries the full burden and does well: it discloses result shape (matching tasks, best first, with matched lines), that a chat read back includes 'why' per reply, that agent/task ids come from a prior result, and that days/limit scope the output. It omits permission/ownership scoping details beyond 'the user's agents,' pagination, and any error behavior.

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?

Dense and front-loaded: the primary use case comes first, then parameter meanings, then the sibling exclusion. It is one long semicolon-chained paragraph, which makes the mode mapping harder to scan than a short mode list would, but there is very little wasted text.

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?

A six-parameter, multi-mode retrieval tool with no annotations and no output schema is fully described in terms of what is returned (tasks with matched lines, chats with 'why', decisions with rationale). Remaining gaps are minor: default/max limits live only in the schema and nothing is said about result volume or failure modes.

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?

At 67% schema coverage the description compensates well for the undocumented `query` and `days` fields, defining query as words to look for and days as a last-N-days window, and clarifies that agent/task must be drawn from a prior result. It also explains the semantic interaction between `decisions` and `query`/`agent`. Only `limit` is left entirely to the schema.

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 description gives a specific verb+resource (search prior agent runs/chats in Caddie) and enumerates the distinct modes: text search, read a specific chat via agent+task, list latest tasks, and the decisions variant. It explicitly names search_notes as the sibling that holds saved findings. It does not, however, differentiate itself from the active `decision_log`/`decisions_read` siblings even though it exposes a `decisions: true` mode that overlaps with them.

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?

Explicit triggers are given ('when the user mentions something from earlier, or before redoing a lookup another run may have done'), along with an exclusion routing to search_notes for saved note findings. Mode selection is spelled out for each parameter combination (query vs agent+task vs nothing vs decisions).

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