get_agent_instructions

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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavior: with no arguments the tool returns the orchestration script, while passing a persona changes the response to one persona's instructions. It does not address invalid persona values or error behavior, but the presence of an output schema and the read-only annotations lower the burden.

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 with no filler, and the most important fact ('Mandatory first call... returns the orchestration script') is front-loaded. The second sentence packs the only parameter semantics into a compact list. This is an appropriately sized description.

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 one-optional-parameter, read-only, output-schema-bearing tool, the description is largely complete: it covers call ordering, the no-argument default, and the valid persona set. The only notable gap is that the persona list is not explicitly bound to the agent_name parameter, though the schema's single property makes that inference easy. It does not need to describe return values because the output schema already covers them.

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 only defines an optional string agent_name with a default of '', so the 0% description coverage forces the description to carry the semantics. It does so by enumerating the acceptable persona values ('reader / format / drafter / verifier / refiner / overseer') and by stating that omitting arguments yields the orchestration script. It never explicitly names agent_name in the prose, but with a single parameter the mapping is inferable.

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 states a specific verb and resource: 'returns the orchestration script,' and clarifies that passing a persona ('reader / format / drafter / verifier / refiner / overseer') returns that persona's instructions. This is unique among the sibling tools, none of which mention orchestration scripts or persona instructions. It is slightly oblique because 'Mandatory first call' is more usage guidance than a purpose statement, so the core purpose is clear but not maximally explicit.

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?

'Mandatory first call' explicitly tells an agent to invoke this before anything else, which is strong when-to-use guidance. It also tells the agent the two calling modes: no arguments for the full orchestration script, or one persona for a persona-specific script. It does not mention when not to use it or name alternative sibling tools, but for an orchestration entry point that omission is minor.

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