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

With no annotations supplied, the description carries the full burden and discharges it: it discloses default and maximum page size, that paging runs newest-first while each page is returned oldest-to-newest, that text over 1000 characters is truncated, that an unknown instanceKey yields an empty list rather than an error, and that olderRunsHiddenByPlan replaces the whole result. These are exactly the non-obvious behaviors an agent needs before calling.

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?

The most load-bearing facts (what it returns, where instanceKey comes from) are front-loaded, and the pagination, filter, and result-shape details follow in a logical order. It is dense to the point of being a single wall of clauses, but no sentence is redundant.

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?

There is no output schema, yet the description spells out the return shape including field names, timestamp format, hasMore, and nextOffset, plus the special olderRunsHiddenByPlan case. For a ten-parameter, unpaginated-looking read tool this is complete enough to call correctly on the first attempt.

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 0%, so the description must compensate, and it largely does: offset is defined as skipping N newest messages, limit gets default 100 and max 1000, nodeId is constrained to one block, textFilter is 'text contains', and period's four values are enumerated with from/to as the mutually exclusive alternative. Only workspaceId is left unexplained, which is a minor gap against ten parameters.

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 opening clause states a specific verb and resource ('Log messages one run wrote') and immediately scopes it to a single run, which distinguishes it from run-listing siblings like list_flow_instances and from block-level siblings like get_flow_instance_block. It also names the tool that produces the required instanceKey, so the resource identity is unambiguous.

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?

It tells the agent where to obtain instanceKey (list_flow_instances) and how to choose between the two time-filter modes ('period ... or a custom range from/to; not both'), which is explicit exclusion guidance. What is missing is a direct statement of when to prefer this tool over get_flow_instance or get_flow_instance_block when debugging a failed run.

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