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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety and determinism are covered. The description adds multi-language support and the fact that counting is exact, which is useful context, but it doesn't discuss token limits, output format, or error conditions. With annotations carrying the safety profile, a 3 is appropriate—the description adds some behavioral value but not rich operational detail.

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?

Two tight sentences that front-load the list of metrics, then justify the tool's existence with the token-miscounting rationale. Every sentence earns its place. It is slightly long but not wasteful; the enumeration is necessary for precision.

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 read-only counting tool with no output schema, the description covers what the tool returns (the list of metrics) and when to use it. It is nearly complete. The only minor gap is not specifying the output structure, but since there is no output schema, the description's enumeration of metrics is sufficient for an agent to know what to expect.

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 50%: the 'locale' parameter is well documented in the schema as a BCP 47 tag for language-specific rules, but the 'text' parameter has no description. The description implies the tool works for any language, which indirectly explains locale's purpose, but adds no syntax or format details for the 'text' parameter beyond what the schema provides. Baseline 3 is correct when the schema does the heavy lifting.

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 specific verb (count) and resource (text) and enumerates exactly what is measured: characters with/without spaces, emoji handling, words, sentences, paragraphs, lines, UTF-8 bytes, reading and speaking time. This level of detail distinguishes it from siblings like diff_text and check_json, which an agent can immediately rule out.

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 explicitly says when to use it ('Language models see text as tokens and miscount — never estimate counts or check length limits yourself; call this tool') and implies when not to (no estimating). The guidance is prescriptive and unambiguous, leaving no room for the agent to choose an alternative way to count.

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