Записати FILE-блоки з відповіді GLM

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

With no annotations, the description carries the full burden and discloses useful behavior: it consumes a run result, writes FILE: blocks, and rejects secrets or paths outside GLM_WRITE_ROOTS. It does not mention overwrite behavior or failure semantics, but the stated security constraints go beyond a generic 'writes files' statement.

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 concise sentences contain the core action, default source, and key constraints with no redundant filler. The most important information is front-loaded.

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 simple one-parameter tool, the description covers the main action, default selection, and safety boundaries. However, there is no output schema and the description does not indicate what the tool returns or how it reports rejected blocks, which leaves some ambiguity for an agent needing confirmation of success.

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?

The input schema only lists run_id as an optional string with no description. The description adds meaning by explaining that the run result is used and that the default is the most recent done run, effectively documenting run_id as optional and clarifying its default behavior.

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 clearly identifies the verb (writes/applies) and resource (FILE: blocks from a GLM run result), and specifies the default source as the last done run. It is distinguishable from siblings like glm_result because it performs file writes rather than just returning the result.

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?

The description implies the tool is used after a run to apply its FILE outputs, but it does not explicitly state when to use it instead of glm_result, glm_run, or plan_append, nor does it mention conditions like 'use only after a completed run'. The only guidance is the default selection of the last done run.

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