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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is covered; the description's duplication warning adds concrete consequence beyond the idempotentHint flag. It does not say what is returned (e.g., the new id), what happens with an invalid category or unknown ref_id, or whether failed validation partially writes.

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 fragments, front-loaded with the WRITE marker, with zero filler. The duplication caveat and endpoint are each one clause and both earn their place.

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 10-parameter mutation with no output schema, the definition covers the write semantics but omits the return value and required-field expectations a caller needs to chain on (e.g., retrieving the created transaction). Adequate given the annotations, but not complete.

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 coverage is 60% (date, amount, ref_id, vendor, category, ref_type documented), so the schema carries most of the burden and the description adds nothing about parameters. The four undocumented fields (type, keywords, description, check_number) get no compensating explanation, but type is self-evident from its enum.

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 specific verb plus resource and the domain object: 'record an income or expense transaction in the farm's books', with the endpoint POST /transactions. That cleanly separates it from the read siblings (list_transactions, get_transaction), though no sibling is named explicitly.

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?

'Creating twice records it twice' is a genuinely useful warning against naive retries, but there is no explicit when-to-use framing against list_transactions/get_transaction, and no prerequisites (e.g., that category keys or ref_id entities must already exist). Guidance is implied rather than stated.

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