compact_evidence

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

With no annotations, the description carries the full behavioral burden. Compaction implies discarding material, yet it never states whether evidence is mutated, dropped, or merely summarized, nor whether the operation is reversible or permission-gated. The one behavioral claim made ('retaining source refs') is useful but far from complete.

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?

A single front-loaded sentence with no padding; the retained-refs constraint is stated before the prioritization rule. Only the unexplained 'Reality proof' jargon slightly undercuts clarity.

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?

An output schema exists so return values need not be described, but for a mutation-flavored tool with zero annotations and 0% parameter coverage the definition is too thin to call safely. It omits the very behavioral facts an agent needs before compacting evidence.

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%, so the description is expected to compensate. It never explains the shape of the `evidence` array items or what `max_items` truncation does to the retained refs, leaving both parameters undocumented in schema and prose alike.

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?

Names a specific verb+resource ('compact evidence') and adds two qualifiers (retain source refs, prioritize direct Reality proof). However 'compaction' semantics and the undefined jargon term 'Reality proof' leave the exact transform ambiguous, and it does not distinguish itself from siblings like validate_evidence or resolve_precedence.

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?

There is no statement of when to use this tool, when not to, or which sibling to prefer. In a family of seven evidence-related tools, the agent gets no routing signal at all.

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