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

Goes well beyond the annotations by disclosing the full-object replacement semantics, null-to-inherit behavior, the exhaustive validation failure list (unknown ids, editing fact text, empty text, size caps, hiding a consumed fact row), and the grandfathered re-validation exemption. This is rich behavioral context an agent needs before mutating.

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-loads the core operation and target level, then details the entry shape and failure modes. Dense and information-packed with little waste, though the inline JSON shape makes sentences long and harder to scan.

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 3-param nested-object mutation with no output schema, the description covers shape, semantics, and failure modes thoroughly. It does not describe the successful return/response, which is the main remaining gap.

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 100%, so baseline is 3, but the description adds real meaning: the per-block entry shape (enabled/text/order/hidden_rows), which fields apply to guidance vs fact blocks, and null semantics. in_workspace's non-persistence is also reinforced.

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 (Replace) and resource (stored prompt-block overrides at one level), and disambiguates the target level via agent_id presence. An agent can distinguish it from prompts_blocks_get/preview/registry without opening the 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?

Explains the full-replace contract, that prompt_blocks is the FULL desired object, how to remove an entry (null → inherit), and points to prompts.blocks_registry for valid ids. It gives clear context but does not explicitly contrast with siblings like prompts_blocks_preview or prompts_update.

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