set_task_security

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

There are no annotations, so the description carries the full burden. The description labels the operation as WRITE and clarifies that the policy is not a sandbox, but it does not disclose side effects, whether existing security settings are overwritten, permission requirements, or what happens to the policy once set. These are important behavioral gaps for a mutation tool without annotation support.

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 description is two short sentences, front-loads the operation kind ('WRITE'), and each sentence adds substantively distinct information. There is no filler, repetition of the tool name, or redundant restating of schema properties.

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?

The tool has 9 parameters, no output schema, no annotations, and a sparse description. An agent cannot tell what response format to expect, how the policy is applied, how approval arrays interact with other fields, or what the 'decision point' semantics mean for a client. The description is not enough to confidently and correctly invoke such a specialized security tool.

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 schema has 0% description coverage, and the description mentions none of the nine parameters. It only gives high-level context about a security policy and adds no meaning for required fields like projectId and taskId or important arrays like allowedActions and deniedResources. The agent is left entirely to infer the semantics of the parameter names without additional intent or example.

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 opens with 'WRITE' and explicitly states it 'Sets a portable task security policy,' providing a clear verb and resource. It further differentiates this tool from similarly named siblings by explaining that the policy is 'a decision point for cooperating clients' and not a sandbox for external tools. This is enough for an agent to distinguish it from set_task_lifecycle, set_task_intent, and get_task_security.

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 gives clear context about when this tool is relevant by stating the policy is for cooperating clients and explicitly says it does not sandbox unrelated external tools. However, it does not name an alternative tool or spell out when to choose a sibling like get_task_security or check_task_access, so it misses the highest bar for explicit when/when-not guidance.

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