available_log_fields

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

With no annotations provided, the description carries the full behavioral burden and discharges it: it discloses the sampling strategy (stratified across `kubernetes.container_name` via FIELDS_STRATIFY_FIELD so rare container types contribute), the extraction method (walks each doc's `_source`), deduplication, and result grouping that collapses `kubernetes.annotations.*`. It also notes enrichment from the field-caps API when available. These details materially affect how the agent should interpret the returned field list.

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?

The purpose is front-loaded in the first sentence, followed by usage guidance and a closing tip; every paragraph carries information. The one redundancy is restating the 'call once / rarely re-call' point in two separate sentences, which costs a little tightness.

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 10-parameter, no-output-schema tool, the description covers the essentials: what is returned (deduplicated, type-annotated, aggregatability-annotated field paths), how it is shaped (grouped/collapsed), and when to invoke it. It does not describe response envelope details or any bound on the sampled document count, which is a minor gap given there is no output schema to fall back on.

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 70% and the schema already documents each parameter in detail (level, query, query_dsl, include/exclude_filters, time windows). The description only gestures at parameter behavior ('found in a sample of matching log docs', the stratify env var) without adding syntax or semantics beyond what the schema states, so the baseline of 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 gives a precise verb and resource: 'Returns every populated field path (dotted) found in a sample of matching log docs,' plus the schema-discovery intent ('learn the schema: what `aggregate_fields` and `display_fields` paths are valid'). This is unmistakably distinct from the sibling search/inspect/summarize tools, which operate on log content rather than on the field inventory.

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?

Explicitly states when to call it ('Call this ONCE at the start of a fresh investigation'), when not to ('Subsequent investigation turns rarely need to re-call this because the schema is stable across queries'), and how to pair it ('pair it on the very first turn with a `summarize_logs` call (in parallel)'). This is a textbook when/when-not/alternative instruction.

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