check_injection

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

With no annotations, the description must carry the behavioral burden, and it does disclose two genuinely useful traits: the detection is lexical (keyword-based, so semantic/paraphrased attacks will likely slip through) and it is an intentionally reduced "lite" version. It stops short of saying what is returned (boolean? score? matched spans?), any threshold, or whether untrusted input is stored or logged.

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 short fragments, front-loaded with the core identity and no filler. It is efficient, though the trailing external-repo reference is arguably marketing rather than agent-usable guidance.

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 security-adjacent screening tool with no annotations, no output schema, and zero parameter documentation, the description is substantially under-specified. An agent cannot know what a call returns, what the failure/negative case looks like, or how the optional "tool" argument changes behavior.

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 0% and the description explains neither parameter. The required "text" is inferable from the tool's nature, but the optional "tool" parameter is completely opaque — its purpose, expected format, and effect on results are undocumented in both the schema and the description.

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?

"Lexical prompt-injection pre-filter" names the resource (prompt injection) and the mechanism (lexical pre-filter), so an agent can infer this screens text for injection attempts. But it never states the action in verb form (detect? score? block?) or what the result represents, and it draws no distinction from siblings such as verify_claims.

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 "(lite)" marker hints that a stronger option exists, but that option is an external GitHub project (gamai-io/gamai-guard), not any of the listed sibling tools, so no selection guidance between check_injection, verify_claims, or the receipt tools is given. There is no statement of when this should be preferred, or when it is insufficient.

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