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

No annotations are provided, so the description carries the full burden. It does disclose a genuinely useful non-schema trait — a 0.002 USDC cost per invocation — but says nothing about whether the guard blocks the write, is advisory, what happens on a rejected write, or what auth is needed.

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 zero filler; the screened threat classes come first and the price trailer is compact. It is efficient, though the terseness contributes to the coverage gaps elsewhere.

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 explained, but with zero annotation coverage and 0% schema description coverage for two nested-object parameters, an agent cannot tell what to put in 'write'/'policy' or what the guard does with a failing write. The description is too thin for a guard tool of this complexity.

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 both parameters are undescribed nested objects ('write', 'policy'); only the example hints at their shape (source.uri, content.fact, memory_id, max_bytes, ttl_seconds). The description adds no parameter meaning beyond the vague 'missing provenance' hint, so it fails to compensate for the coverage gap.

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?

Specific verb ('screen') plus resource ('persistent memory writes') and an enumeration of the three threat classes it looks for (poisoning, unsafe instructions, missing provenance). It reads clearly against most siblings, though it never explicitly distinguishes itself from the closely named agent_memory_provenance.

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 name and the phrase 'persistent memory writes' imply the trigger point (before committing a memory write), but there is no explicit when-to-use, no statement of when this guard is unnecessary, and no named alternative among the many preflight/guard siblings.

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