memory.query_at

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

Since no annotations are present, the description carries the full burden. It clearly states that the tool performs a query (not mutation) and has bitemporal semantics. However, it does not disclose potential performance implications (e.g., time-travel queries may be slower) or access control, which would elevate it to 5. Still very strong.

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?

Four sentences, zero waste. The first sentence gives the purpose, the second gives usage guidelines, the third gives an exclusion warning, and the fourth provides a concrete example. Maximally efficient.

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 output schema exists, return values need no explanation. The tool has 6 params but only 1 is required, and the description explains the key param (point_in_time) and one filter (project). For a read query tool with clear sibling differentiation, this is contextually complete.

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?

With schema coverage at 0%, the description must compensate. The example usage 'memory.query_at(project='CORE', point_in_time='2026-01-01T00:00:00Z')' clarifies the format for the required point_in_time parameter and shows how the optional project filter works. The description also implies that point_in_time is an ISO 8601 timestamp. However, other parameters like category, memory_scope, memory_branch, and limit are not explained, which prevents a 5.

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 uses specific verb+resource: 'Consulta memórias que estavam ATIVAS num instante passado' (queries memories active at a past point in time). This clearly distinguishes it from the sibling memory.query (current state). The reference to bitemporal ISO 8601 further specifies the temporal nature.

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?

Explicit guidance is provided: 'Use when: auditoria / reconstruir estado histórico' and 'Do NOT use for: estado atual (memory.query)'. This directly addresses when to use vs. the most similar sibling tool, with no ambiguity.

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