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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds substantial value beyond that: coverage starts in 2020 and varies per tribunal, empty results return an `ausencia` block with possible reasons, and each returned item contains the full communication text. No contradiction with annotations.

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 well-organized: purpose first, then item content, then important caveats and empty-result behavior. Every sentence contributes meaning, and nothing is repeated or padded.

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 read-only search tool with no output schema, it is unusually complete: it covers scope, coverage limits, empty-result structure, and how to confirm absence of a process. It falls just short of full completeness because several input parameters remain under-specified and the non-empty result structure is only outlined, not detailed.

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_description_coverage at 0%, the description must compensate for the schema. It explains the main semantic filter dimensions (OAB, lawyer, process number, tribunal, date) but does not clarify parameters like `meio`, `texto`, `pagina`, `nome_parte`, or `itens_por_pagina`. Partially helpful, but with clear gaps.

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 a specific verb and resource ('Busca publicações/intimações no DJEN') and lists concrete filter dimensions: OAB, lawyer name, process number, tribunal, and date. It also explicitly distinguishes this tool from jurisprudence/ementa databases and process registries, clearly separating it from siblings like jurisprudencia_buscar and processos_buscar_por_nome.

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 states when to use the tool (search published DJEN communications by the given criteria), when not to use it (not for jurisprudence, not a process registry), and names an alternative (datajud_get_processo) for historical confirmation when results are empty. This is explicit and actionable routing guidance.

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