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

Annotations already declare idempotent=true, destructive=false, readOnly=false. The description adds genuine behavioral context beyond them: bank-synced entries retain the bank's account, amount and date, which is a real constraint an agent cannot derive from the schema. It stops short of stating permissions, side effects on linked data, or response behavior.

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?

Front-loaded with the core action and partial-update rule, then the format details. Three compact sentences with no filler, though the closing month/period sentence does not map to any parameter and is arguably wasted.

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 13-parameter mutation with 0% schema description coverage and no output schema, the description covers partial-update semantics and value encodings but omits the meaning of most fields, especially the transfer-related trio. It is minimally viable for correct invocation of simple fields but insufficient for the full surface.

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 13 parameters, so the description carries the burden and only partially meets it. It explains amount encoding (minor units, 45000 = 450.00) and date formats, but leaves the relationships between amount/toAmount/baseAmount, the transfer fields (toAccountId, toCurrency), isRefund, and type undocumented. The 'month is a budget period YYYY-MM' sentence references a format with no corresponding schema parameter, which adds confusion rather than clarity.

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 (change) and resource (an entry's fields) and clarifies partial-update semantics with 'only those you pass'. It does not differentiate itself from the close sibling bulk_update_transactions, so an agent must still infer when to use one vs the other.

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?

Usage is implied by the partial-update note ('only those you pass') and the bank-synced caveat, but there is no explicit when-to-use guidance and no mention of the alternative bulk_update_transactions or add_transaction. The agent must infer the selection rule.

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