save_evidence

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 says evidence is 'recorded,' but does not explain side effects, return behavior, whether it creates a new evidence entry, or what happens on validation failure. This is a lean description that leaves the tool's runtime behavior largely implicit.

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 filler. Every part adds meaning: the action, the resource, the context, and the examples of evidence.

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 and no annotations, the description is the only source of guidance, but it does not explain what the tool returns, that evidence is tied to a challenge_id, or what constraints apply. The operation is simple, yet several practical details an agent would need for correct invocation are missing.

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 covers 50% of parameters with descriptions (content, command_text), and the description adds examples like 'hypothesis, observation, command output' that map onto the evidence_type enum. However, it does not clarify challenge_id semantics or the conditional relationship between command_text and evidence_type 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 uses a specific verb ('Record') with a clear resource ('evidence') and gives concrete examples of what counts as evidence: hypothesis, observation, command output. This distinguishes it from siblings like list_evidence and create_event, which are clearly different actions and resources.

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?

'During solving' provides a clear context for when this tool should be used, and the examples of evidence types help an agent decide that this is the right place for hypotheses, observations, and command outputs. It does not explicitly name alternative tools or exclusion cases, but the context is clear enough for a simple recording operation.

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