erase_log

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

With no annotations, the description carries the full burden and does a good job: it declares the read-only guarantee, identifies the backing file, the schema of the report, and discloses a partial-failure behavior (unparseable lines are named by number). It omits pagination or output-shape details, but the core behavioral profile is well covered.

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 sentences, front-loaded with the resource identity and followed by the scope/read-only caveats. Dense but no filler; the parenthetical schema name is the only slightly heavy element.

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 single-parameter read tool with no output schema and no annotations, the description is nearly self-sufficient: it explains the source file, the schema name, the record provenance, and the malformed-line handling. An agent could call this correctly without further 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?

There is one parameter with 100% schema coverage, so the schema already documents `path` as a subpath defaulting to the project root. The description adds no further param meaning, so the baseline 3 applies.

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 names a specific resource (the applied-erase audit trail at .ce/erase-log.ndjson) and what it contains (records appended by `ce erase --apply` or the GUI, plus unparseable lines). The read-only framing distinguishes it from the sibling `erase`, which implies the opposite operation. It is clear without explicitly stating the verb 'read'.

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 'Read-only — nothing here can apply or append' line implicitly tells the agent to use this for inspection rather than mutation, and contrasts with the `erase` sibling. However, there is no explicit when-to-use guidance, no statement of when NOT to use it, and no named alternative for inspecting erase history.

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