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

With no annotations, the description carries the full burden and does real work: it discloses that the analysis is LLM-based (hence non-deterministic), that it returns a fixed per-clause verdict vocabulary, and — most importantly — that the tool is currently disabled via a TOOL_TEMPORARILY_DISABLED response. It stops short of noting cost, latency, or text-size limits, and does not flag that both parameters are technically optional despite the tool being useless without text.

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 tight sentences, front-loaded with purpose and output shape, with no filler. The one structural weakness is that the most actionable fact — the tool is temporarily disabled — is buried at the end rather than leading, so an agent skimming the opening clause could call a dead tool.

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 two-parameter, no-output-schema tool, the description covers input mode, output vocabulary, scope (15 mandatory clauses), and availability status — enough to call it correctly or avoid it. What is missing is how PARTIAL is decided and what happens when the pasted text covers only some of the 15 clauses.

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 100%, so both contract_text and provider_name are already documented in the schema, including the plain-text-from-PDF guidance. The description adds only the imperative "Paste contract text," which restates the schema rather than extending it (e.g., no guidance on minimum text length or how partial sections affect verdicts). Baseline 3 applies.

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 names a specific verb and resource — LLM-based analysis of contract text against DORA Article 30 — and states the exact output shape (PRESENT/PARTIAL/MISSING per clause across all 15 mandatory clauses). It does not explicitly distinguish itself from near-neighbors like check_contract or contract_analyze, so an agent still has to infer which contract tool to pick.

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?

"Paste contract text" implies the calling context (raw contract text in hand, no pre-registered contract ID), which is useful and indirectly separates it from tools that act on stored contracts. However, there is no explicit statement of when to prefer this over check_contract or contract_analyze, and no prerequisites or exclusions.

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