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

Annotations already declare non-readonly/non-destructive behavior; the description adds real value beyond them: it may only reference existing ids, never fabricates amounts, requires 'reconcile' authorization, and is a proposal subject to human approval. It doesn't cover what happens on rejection or prerequisite state.

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?

Dense but front-loaded: the core action and its key constraint ('only existing ids, never fabricates amounts') come first, followed by the approval/auth model and parameter listing. No filler sentences.

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 proposal-style tool with no output schema and sparse schema descriptions, it covers the essential behavior, authorization requirement, and all parameter names. Missing only edge details such as what a successful proposal returns or how failures are surfaced.

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?

With schema coverage at only 11%, the description carries the load by naming all nine arguments and clarifying that target_ids is a list of source ids and that reasoning/confidence/model/finding_ref are optional. It leaves year/month and bank_txn_id formats unspecified, but adds meaning well beyond the bare schema.

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?

States a precise verb (propose) and resource (bank match), plus the concrete operation: linking an unmatched bank row to one or more existing GL/subledger candidates. This distinguishes it cleanly from siblings like create_proposal or propose_voucher.

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?

Gives clear context: it applies to unmatched bank rows, the LLM proposes and a human approves, and it requires the 'reconcile' permission. It does not explicitly name an alternative sibling or state when-not-to-use, so it falls short of a 5.

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