delimit_agent_policy

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

The description discloses side effects: writing occurs when any of the listed parameters are provided (set_agent_policy), and empty/no-changes results in read-only behavior. It also enumerates allowed values for access levels and boolean flags. However, it does not cover authentication needs, rate limits, or error states, which would enhance transparency. Since no annotations exist, the description carries the full burden and does a good job but has minor gaps.

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 well-organized with clear sections (When to use, When NOT to use, Sibling contrast, Side effects, Access levels). Every sentence serves a purpose, no redundant information. It is concise yet comprehensive, front-loaded with the primary purpose.

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?

Given 7 optional parameters and no required ones, the description covers usage scenarios thoroughly. It explains the tool's role, when to use alternatives, side effects, and valid parameter values. The presence of an output schema (mentioned in context) means return values need not be explained. The description is sufficient for an agent to correctly invoke the 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?

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining that ledger/memory/evidence use access levels (read-only, read-write, none), deploy/secrets use boolean flags, and custom_constraints is comma-separated. It also notes that empty model lists all. This provides context beyond the schema's brief descriptions.

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 states 'Set or view per-model governance permissions' and elaborates on what that entails (inspect or modify access policy for AI models on ledger, memory, evidence, deploy, secrets). It distinguishes from siblings by naming delimit_gov_evaluate and delimit_project_config as alternatives, making the purpose 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?

Explicitly provides 'When to use' and 'When NOT to use' sections, specifying that this tool is for configuring per-model policy and not for runtime evaluation (use delimit_gov_evaluate) or session policy (delimit_project_config). It also contrasts with delimit_gov_evaluate, giving clear guidance on tool selection.

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