proximo_recall

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

Beyond the readOnlyHint annotation, the description reveals that this is a snapshot from local memory, not live data, and that entries carry as_of and age_seconds stamps. It also clarifies that not_seen_since is an observation, not proof of deletion, and that journal entries are summaries only — substantial behavioral detail that the annotation alone does not convey.

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 description is dense but highly efficient; every sentence and clause adds operational value. It front-loads the most important distinction (memory vs live) and uses compact, scannable phrasing like 'stamped {source:'memory', as_of, age_seconds}' and 'not_seen_since (last observed before the window — a fact, not a claim the entity is gone)' to pack maximum insight into limited text.

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?

Given the tool's complexity (optional diff windows, journal integration, memory configuration) and the presence of an output schema, the description covers the essential semantics: data freshness, server-side counting, derivation/rebuildability, and safe usage guidance. It fully equips an agent to decide when and how to invoke the tool without missing behavioral nuances.

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?

Although the schema already documents all four parameters with descriptions, the tool description adds critical cross-parameter behavior: `since` activates diffs (appeared, status_changed, not_seen_since), `journal=N` includes diagnosis digests and is windowed by `since`, `query` narrows rows but counts cover the whole estate, and `detail` controls row depth. This enriches meaning well beyond the individual schema entries.

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 opens with 'READ-ONLY: the estate map from local Tier-1 memory' which clearly identifies the resource and operation. It explicitly contrasts with 'NOT a live PVE read' and enumerates the exact return contents (counts, entity rows, stamps), distinguishing it from sibling audit and tool-discovery tools.

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 description gives explicit when-to-use and when-not-to-use guidance: 'For live state use pve_list_guests / pve_cluster_resources' while this tool serves memory-derived summaries. It also advises trusting guest_summary for guest-count questions and explains that `since` and `journal` are optional for diffs and digests, providing clear context for choosing this tool over alternatives.

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