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

Beyond the read-only annotations, the description discloses the output behavior: newest-first ordering, one row per changed field with old and new values, a created row, and a deleted row containing last values as JSON. It also states the required access scope, budget.read, and confirms the tool works for deleted lines.

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?

The description is front-loaded and mostly efficient, packing useful output details into a compact form. The final sentence 'Answers for a deleted line too' slightly repeats the preceding deleted-row clause, but the redundancy is minor.

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?

With no output schema, the description carries the burden of explaining return values and does so well: row granularity, field coverage, ordering, and special created/deleted rows are all described. Access requirements are also included, making the definition complete for correct invocation and interpretation.

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?

The schema has no description for costLineId, but the description clarifies that it identifies one cost line and that deleted line IDs are also accepted. This meaningfully extends the parameter semantics beyond the bare string 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?

The description states a precise verb and resource: the change history of one cost line. It distinguishes this from listing or updating cost lines by describing the returned rows, including created and deleted rows, so an agent can immediately tell this is the history retrieval tool.

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?

The description gives clear context for when this tool is appropriate: retrieving field-level changes for a single cost line, including deleted lines. It does not explicitly name alternatives such as list_cost_lines, but the history-specific purpose is clear enough to guide selection.

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