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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does reveal that the query is discarded, which is a useful side-effect statement. But it does not disclose whether the tool makes any network calls, whether it logs the query, whether it reads any local state, or what it returns (only the count? a structure?). The word 'discarded' suggests no persistence, but the absence of any statement about network access or return behavior leaves significant gaps.

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 a single sentence with two clauses, so it is concise and front-loaded ('Count characters in a search query'). No wasted words. However, it is so terse that it borders on under-specification; the second clause 'Query discarded' is placed after the core statement, which is acceptable. For a tool with 9 parameters and no annotations, the brevity is not a virtue because it leaves too much unsaid.

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 annotations and no output schema, the description must carry all context. It covers only the core counting behavior and the discard side-effect. It does not explain why 9 parameters exist when the tool is about counting characters in a search query — a significant contextual gap. It also doesn't specify the return value shape, edge cases (empty string, multi-line, Unicode), or relationship to sibling tools like url-path-len. The description is incomplete for a tool with this many parameters and zero annotations.

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%, meaning every parameter has a description, but the description of the query parameter only says 'Search text; discarded after the length check' — this adds little beyond the schema's own text. It doesn't explain how the query string is interpreted (e.g., raw characters vs. trimmed, Unicode code points vs. UTF-16 code units, whitespace handling). The other parameters (ref, url, city, feed, host, json, path, zone) are documented in the schema but the description doesn't clarify why they exist in a search-query-len tool or whether they are all similarly discarded. The description fails to add meaningful semantics beyond what the schema already provides.

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 verb ('Count') and a resource ('characters in a search query'), and adds a scope constraint ('Query discarded'). However, the tool name search-query-len is clear enough that the description merely restates the name, and it does not clarify what aspect of the query is counted (characters? tokens? bytes?) beyond the word 'characters'. It also doesn't distinguish itself from sibling tools like url-path-len or validate-json beyond the name, so the description adds little clarifying value.

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 gives one behavioral note ('Query discarded') but no when-to-use guidance. It does not state when to choose this over sibling tools like calc-eval or validate-json, nor any context like 'use when you only need a length check'. The 'discarded' note is a privacy/usage hint but not a usage guideline. No prerequisites or examples are given.

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