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

Annotations already cover read-only, idempotent, closed-world and non-destructive, so the bar is lower, and the description still adds real context: outputs are 'cited', provisional updates are 'separately dated', and the tool carries 'no score, credit or execution authority'. Those are useful disclosure about provenance and epistemic status that the annotations cannot express, though return format and history behaviour remain undisclosed.

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, front-loaded sentences with no filler; the domain is stated first and the caveats follow. It is terse to the point of being telegraphic, which costs a little clarity but wastes nothing.

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 and one required identifier, the description should say what slug denotes and what a caller receives; it conveys the content categories and the no-authority stance but not the identity or history semantics. Adequate as a sketch, incomplete for correct invocation.

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 only 33% - only as_of is documented, while slug (the sole required parameter) and include_history are bare. The description never mentions any parameter, at best implying period handling via 'keep each period explicit', so it does not compensate for the coverage gap and an agent gets no help on what slug identifies or when include_history matters.

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 enumerates the content domain (NPA changes, PCR definitions, capital scope) and the covered institution types (banks/SFBs/UCBs), which is more than a restatement of the name. But it is written as a noun phrase with no verb, so it never states what the tool actually does with that content, and it draws no boundary against close siblings such as bank_npa_reconciliation or rbi_supervisory_tape.

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?

There is no when-to-use guidance and no named alternative; 'keep each period and provisional status explicit' is an instruction about how to present output, not about when to select this tool. The only conditional, 'provisional business updates when accepted', describes data inclusion rather than invocation context, leaving the agent to infer selection from the title alone.

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