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

With no annotations, the description carries the full burden and does supply two real behavioral facts: results are capped at 400 and each series is returned with its latest value. It omits ordering, anchoring of the pattern, and what happens on a malformed pattern or zero matches.

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 core contract (pattern match, latest value, 400 cap) is front-loaded before the examples. The trailing list of six example families is dense but each illustrates a distinct domain, so it mostly earns its place; splitting the run-on single sentence would improve scannability.

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 single-parameter read with no output schema, the description covers the input syntax, the return shape ('each with its latest value'), and the result cap. Only ordering and edge-case behavior are absent, which are minor for this tool.

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%, so the description must compensate, and it does: '% any run, _ one character' defines the LIKE syntax the bare 'string' type leaves unexplained, and the example patterns demonstrate real values. It stops short of saying whether the pattern is matched against the full code or a prefix.

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 and resource: it returns every series whose code matches an SQL LIKE pattern, each with its latest value. The LIKE-pattern semantics plus the 'family' framing let an agent distinguish this from get_series or search_series without opening a schema, 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?

Usage is only implied via the six example family patterns, which show the intended shape of a call. There is no explicit statement of when to prefer this over get_series, search_series, or get_datum, and no guidance on invalid patterns.

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