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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description still adds two non-obvious behaviors: it scans only the latest 200 decisions before applying from/to (so old windows can silently return empty) and the headline-language fallback logic for English vs stored Arabic text. Neither is derivable from the schema or annotations.

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 scope and field list, then usage, then the scan caveat, then sibling pointers — a sensible order with no filler sentences. The headline-language parenthetical is the densest part and takes a re-read, which keeps it off a 5.

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 5-parameter read tool with an output schema, the description covers what an agent needs to call it correctly: scope, ordering, the silent truncation risk on old windows, language behavior, and where to go for the underlying text. Nothing material is left to inference.

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 100%, so the baseline is 3; the description goes beyond it by explaining that from/to are applied *after* the 200-decision scan (changing how an agent should interpret an empty result) and by spelling out the lang fallback behavior (stored English headline, else generated one). It does not add format details for limit or dates, which the schema already covers.

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?

"Rate-decision history of ONE central bank, newest first" names the verb, resource, scope and ordering in one clause, then enumerates the returned fields (hike/cut/hold, bps, rates after, tone score, vote split, dissenters, headline). The uppercase "ONE" and the routing to el7_cb_document / el7_cb_statement_diff make it distinguishable from the many sibling cb_* tools.

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?

It gives a concrete trigger phrase ("what did the bank do at its last meetings") and a secondary use case ("spot a cycle"), then explicitly redirects adjacent needs to named siblings: statement text goes to el7_cb_document, change analysis to el7_cb_statement_diff. An agent can route without consulting other definitions.

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