Style flags

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

Annotations already establish readOnlyHint and openWorldHint=false, and the description adds real behavioral context beyond that: the checks are simple pattern rules with false-positive risk, and the summary output ends with a line listing flagged sentence numbers. Partially overlaps with the output schema, but the caveat about rule-based imprecision is valuable and not encoded anywhere else.

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 purpose and checks, then inputs, then output shape, then caveat — a sensible order. Slightly over-explains the sentence-numbering mechanics and the summary line, which is close to duplicating the output schema.

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?

Given an output schema already exists, the description covers everything an agent needs: purpose, inputs with defaults, numbering convention, and the reliability caveat. Little is missing for a two-parameter read-only analysis 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 coverage is only 50%, but the description compensates: it explains that max_sentence_words is optional with a default of 30 and defines its meaning as 'the length above which a sentence counts as long'. It also names both inputs up front, leaving no ambiguity about what 'text' should contain.

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 ('Flag common style problems in an essay') and then enumerates the exact checks: passive voice, repeated sentence openers, filler words, overlong sentences. This is clearly distinguishable from siblings like readability_scores or word_frequency, which measure rather than flag.

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?

Provides an interpretive directive ('treat them as prompts to reread, not as errors') plus a concrete invocation example ('Flag passive voice and filler words in my draft'). It does not explicitly name when to prefer readability_scores or check_word_limit instead, so it stops short of full routing guidance.

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