graphql-dos-shield

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

With no annotations, the description carries the full burden. It discloses the return values (depth, field count, list multipliers, risk level) and interprets CRITICAL as 'should be rejected', which is valuable behavioral context. It doesn't mention side effects, but 'Analyze' implies a non-destructive operation, and the return description is sufficient for this simple tool.

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 two sentences, front-loaded with the purpose, then the outputs. Every sentence earns its place, with no filler or redundancy. Ideal size for a single-parameter tool.

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 one parameter, no output schema, and no annotations, the description is complete. It states what it does, what it returns, and the meaning of the risk level. There is no significant missing context.

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?

The schema already provides a clear description for the sole parameter 'query' (100% coverage), so the description adds little beyond schema. It doesn't elaborate on formatting, size limits, or edge cases, but the baseline of 3 is appropriate when the schema fully documents the parameter.

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 uses a specific verb ('Analyze') and resource ('GraphQL query complexity'), clearly distinguishing this tool from siblings like query_rewriter (which rewrites) and rate_limiter (which rate limits). It also details the specific outputs (depth, field count, list multipliers, risk level).

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 context is clear: this tool analyzes GraphQL query complexity, and the CRITICAL risk level implies rejection decisions. However, it does not explicitly state when to use this vs. alternatives or mention any exclusions, so it lacks the explicit alternatives guidance seen in higher-scoring examples.

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

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

No annotations are provided, so the description must carry the full burden. It states the tool operates at the 'text-level', indicating a non-executing transformation, and describes the functional changes (strips nesting, truncates fields). However, it does not mention side effects, return format, or any prerequisites. This is minimal viable transparency but lacks deeper behavioral disclosure.

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, front-loaded sentence with no redundancy. Every phrase ('text-level rewrite', 'strips excess nesting depth', 'truncates too many fields') contributes to understanding, making it highly concise and well-structured.

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 output schema, the description should clarify what the tool returns. It says 'rewrite' but does not explicitly state that it returns the simplified query string. The tool is simple, and the description covers the core action, but the missing return value statement leaves a gap for full completeness. A 3 is appropriate.

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 100%, providing baseline 3. The description adds meaning by linking 'strips excess nesting depth' to max_depth and 'truncates too many fields' to max_fields, explaining the purpose of these parameters beyond their raw schema definitions. This enriches the semantics, supporting a 4.

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 tool's function: 'Text-level rewrite of an overly complex GraphQL query: strips excess nesting depth and truncates too many fields.' This specifies the verb (rewrite), the resource (GraphQL query), and the specific actions (strips depth, truncates fields), distinguishing it from siblings like complexity_meter and rate_limiter.

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 implies usage for overly complex queries, which provides clear context. However, it does not explicitly name alternatives or state when not to use this tool versus complexity_meter or rate_limiter. It gives context without exclusions, so a 4 is appropriate.

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

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

With no annotations, the description carries the full burden. It discloses two important behavioral traits: it uses an in-memory sliding window and state resets on cold start. This adds meaningful context for correctness. However, it does not describe enforcement details (e.g., what happens when the limit is exceeded) or return behavior.

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 sentences, with the primary purpose front-loaded and the key behavioral caveat in the second sentence. Every word earns its place.

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 no output schema and no annotations, the description should explain more about return values or enforcement behavior. It covers the core purpose and one limitation (state reset), but lacks details on success/failure responses or how 'enforce' manifests. This is adequate but has clear gaps.

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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description adds no extra meaning about parameters (e.g., how limit and window_ms interact), but the schema already provides the necessary definitions.

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 tool's function with a specific verb ('Check and enforce rate limiting') and resource ('rate limiting for a client'). It distinguishes itself from sibling tools (complexity_meter, query_rewriter) which serve different purposes.

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 implies usage (if you need rate limiting, use this tool) but does not explicitly state when to use it versus alternatives, nor any exclusions. It lacks direct guidance on when not to use this tool or when a sibling would be more appropriate.

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