bind_contract

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

Annotations already declare this a safe, idempotent, closed read, and an output schema covers returns. The description adds genuine behavioral facts beyond that: it refuses placeholder values, refuses compute_local, and has a documented no-path fallback. That value is real but the delivery is opaque, and it never says what 'Extract' does on failure or how the hash is validated.

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?

Three short sentences, front-loaded with the core action and constraint. Tightly sized, though 'ZDH-22' and 'unstamped catalog' are space that does not inform an agent.

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?

Five zero-documented parameters, four of which (mode, scope, bucket, json_text) are never mentioned, is a serious hole for a tool whose whole job is binding a contract. The output schema relieves the return-value burden, but an agent still cannot tell how to pass mode, scope, bucket, or json_text.

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 description coverage is 0% across 5 parameters, so the description carries the full burden and largely drops it. Only 'path' is given meaning (the empty-path fallback); mode, scope, bucket, and json_text are completely unexplained in both schema and description.

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 verb+resource ('Extract stamped contract.hash') is identifiable, but the key nouns ('stamped', 'unstamped catalog', 'ZDH-22') are internal jargon an outside agent cannot resolve. It does not name any of the listed siblings, so the agent cannot place it relative to doctor, readiness_check, or start_project.

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?

It does give a conditional usage rule — 'With no path, copy the hash from the live bootstrap chat_request' — and an exclusion ('Refuse placeholders / compute_local'). However, compute_local is not a listed sibling and no real alternative is named, so the routing guidance only partly helps.

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