propose_pact

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

With no annotations provided, the description carries the full burden. It does exceptional work: it discloses that enforced terms execute atomically while promised terms are reputation-only, that mutual_defence 'summons NO army and the engine never records a no-show,' that breaking a promised term is a public betrayal, that a NAP ends any live war, and that unspecified terms default to 1 day. It also notes that proposals expire in 6h and you can have only 5 open. These are crucial behavioral details an agent must know to avoid misusing the tool.

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 dense and front-loaded: the opening sentence states the purpose immediately, followed by template specifics and critical caveats. It uses paragraph breaks for readability and bold/uppercase for emphasis. However, it is quite long (over 200 words) and could be trimmed without losing critical information, such as merging the enforcement vs. promised explanation into more compact phrasing. Still, it's well-structured and each sentence carries important information.

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 the tool's high complexity (6 parameters, nested objects, two-dimensional space of templates + custom terms), the description is remarkably complete. It covers all parameter semantics, behavioral effects, constraints, edge cases (default day, expiry, limit), and the distinction between enforced and promised terms. With no output schema and no annotations, an agent has everything it needs to construct a correct proposal, including the all-or-nothing atomicity of the package.

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?

Although schema_description_coverage is 100%, the description adds substantial meaning beyond the schema: it explains the semantics of each template and its parameters (days, direction, price_usd, polygon_id) and the difference between enforced and promised terms. It also clarifies that the `from` field in terms uses proposer/acceptor/mutual, which aligns with params.direction. The only minor gap is that it doesn't explicitly map every schema parameter to its template usage, but it provides enough context for an agent to infer them.

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 a clear verb + resource: 'Offer another kingdom a STRUCTURED pact,' and then enumerates four named templates (nap, defensive, passage, land_deal) plus a custom-terms path. It distinguishes itself from siblings like respond_to_pact (offer vs. response) and get_pacts (creating vs. listing). The detail is specific and 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?

The description explicitly explains when to use templates vs. custom terms, what each template does, and how to compose custom terms with up to 5 items in one all-or-nothing package. Although it doesn't name sibling alternatives directly, it contrasts the pact with 'real help in a war,' clarifying that this tool is not for summoning armies. The guidance on defaults (1 day) and limits (6h expiry, 5 open) steers an agent toward correct usage.

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