get_fatal

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

With no annotations, the description carries the full burden; it does disclose the returned payload in useful detail (stack trace, file, line, origin, URL, PHP version, last occurrences), which is real behavioral context. However, it never states that the call is read-only, what happens when a signature is unknown or stale, or how many 'last occurrences' are returned.

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?

One dense sentence with the core purpose front-loaded, followed by the source of the required argument and the payload list. No filler or redundant restatement of the name.

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 simple one-parameter read tool with no output schema, the enumeration of return fields effectively substitutes for a return-value specification. The only gaps are the vague 'last occurrences' (count/format) and the absence of not-found or stale-signature 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 100% and the single parameter is fully documented in the schema, so the baseline is 3. The description restates that the signature identifies a group and comes from list_recent_fatals, adding workflow context but no new meaning about format, case sensitivity, or validation.

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?

States a specific retrieval: the latest record of a single fatal-error group, and enumerates the payload (message, stack trace, file, line, origin, URL, PHP version, last occurrences). It implicitly separates itself from the list tool by scoping to 'one fatal-error group' and citing list_recent_fatals as the signature source, though it never explicitly contrasts with tail_log or list_errors.

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 parenthetical '(signature from list_recent_fatals)' establishes a concrete prerequisite and an implied two-step workflow: list first, then fetch details. It gives no explicit exclusions or guidance on when to prefer this over tail_log or list_errors for inspecting a single error.

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