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

With no annotations provided, the description carries the full burden of disclosing behavior. It states that the query is discarded, which is useful, but it says nothing about the other eight parameters in the schema. The description implies the tool only concerns itself with the query parameter, yet the schema includes unrelated fields like 'url', 'city', and 'json'. This mismatch is not explained, and the absence of any disclosure about side effects, return values, or the handling of non-query inputs leaves the agent under-informed.

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 extremely concise—two short sentences with no filler. It front-loads the primary purpose and includes a key behavioral note about discarding the query. This efficiency is appropriate for a simple tool, though the brevity borders on under-specification given the schema's complexity. Still, for what it says, it is well-structured and easy to parse.

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 tool with nine parameters, no annotations, and no output schema, the description is grossly incomplete. It does not explain what the tool returns (e.g., the character count, its type, or format), nor does it clarify the role of the many non-query parameters. The presence of seemingly unrelated parameters (ref, url, city, etc.) without any explanation of how they interact with the query length check creates significant ambiguity. An agent cannot reliably determine correct invocation or interpret results based on this description.

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 100%, so every parameter is already documented in the schema. The description adds minimal semantic value: it reinforces that the 'query' parameter is the focus, but the schema already describes it as 'Search text; discarded after the length check', which is nearly identical. No additional meaning is provided for the other parameters, so the description does not meaningfully enhance parameter understanding beyond the 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 clearly states the core action: counting characters in a search query. It identifies a specific verb ('count') and resource ('search query'), which distinguishes it from unrelated tools. However, it does not explicitly differentiate from sibling count tools like 'memory-key-count' or 'hn-front-count', and the mention of 'search query' is ambiguous given the schema contains nine parameters, leaving room for confusion about what exactly is counted.

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 provides no guidance on when to use this tool versus alternatives. There is no mention of preferred scenarios, exclusions, or comparisons to sibling tools. The context signals indicate a large sibling set with similar counting tools, but the description offers no routing help, leaving the agent to infer usage from the name alone.

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