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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so safety is covered. The description adds genuine behavioral framing: 'Name matching only', which tells the agent this is not a full-text search and will not surface matches buried in document bodies. It stops short of describing result shape or ordering.

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 before the routing clause, and every phrase earns its place – three siblings are dispatched in a single compact sentence with no filler. Density is high but readable.

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 name search, the definition plus annotations cover invocation fully and no output schema exists to explain returns. The only minor gap is that it never hints at what a result looks like (name list vs. full documents) or how limit defaults, which an agent might want before calling.

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 100%, so all four parameters (query, type, limit, system) are already documented, including the case-insensitive substring semantics of query. 'Name matching only' reinforces the query parameter's scope but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema carries the load.

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 ('Search'), resource ('documents across ALL compendiums') and a scope qualifier ('by name'), which immediately separates it from the filter and page-search siblings. The 'ALL compendiums' emphasis also communicates the cross-pack breadth that no sibling offers.

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 names the triggering condition ('when you do not know which pack holds a monster, item or spell') and routes to three concrete alternatives by name: dnd5e-compendium-filter-* / pf2e-compendium-filter-* for structured filters, compendium-page-search for journal text, uuid-resolve when a UUID is in hand. Nothing is left to inference.

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