Preview filter patterns

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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint, but the description adds behavior they cannot: a filesystem side effect (CSV written to /tmp/log10x-preview-<mode>-<service>.csv), the exact return rendering (fixed-width text, no markdown pipes), and an interaction contract (must_ask_user options, forbidden_next_actions locking configure/mitigate/advise_retriever). This is genuinely additive context beyond structured fields.

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?

Front-loaded with the activation condition and every sentence carries distinct actionable content (trigger, scope, return shape, side effect, allowed next actions, blocked actions). It is dense and slightly run-on toward the end, but there is no filler or repetition of the title/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 workflow-gated preview tool with an output schema, four documented params, and annotations, the description covers the missing pieces an agent needs: precondition, consumed output format, the CSV artifact, and the permitted follow-up actions. Nothing required to invoke or follow up correctly is absent.

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 coverage is 100% and every parameter carries its own description including the mode enum values, so the schema already does the heavy lifting. The description only implicitly echoes the service+mode pairing ('applying a given enforcement mode to a service') and says nothing about top_n or environment semantics, 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?

States a specific verb (preview) and resource (the patterns a given enforcement mode would affect, scoped to a service) and explicitly frames it as a no-side-effect dry run. The sequencing cue referencing log10x_explain_mode and the drill-down reference to log10x_pattern_detail lets an agent distinguish it from the ~50 sibling tools without opening any schema.

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?

Gives an explicit trigger ('CALL THIS AFTER log10x_explain_mode when the user picks Preview'), an explicit scope caveat ('before any action is taken'), a named alternative next step ('drill into pattern #N calls log10x_pattern_detail'), and locks three specific sibling tools until the user commits. There is essentially nothing left to infer about when to select this tool.

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