query_source_entities

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

With no annotations, the description carries the full burden. It discloses boundedness and cursor stability, but says nothing about read-only safety, what filters are actually supported, what happens on empty results, timeout/byte-cap behavior despite max_bytes and timeout_ms defaults, or any permission requirements.

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?

A single front-loaded sentence with no filler, which is structurally clean. However, its terseness is achieved through under-specification rather than information density — the terms used ('exact facts') are evocative but opaque.

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?

An output schema exists so return values needn't be described, but for a 13-parameter query tool with no annotations and zero schema documentation, the description leaves far too much unexplained — filter semantics, view/layer selection, and the pagination contract are all missing.

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 0% across 13 parameters, so the description must compensate and it barely does — only 'bounded SQL filters' and 'keyset cursors' loosely gesture at filters and cursor params. Spatial (bbox), structural (view, layer, layout, dwg_type), text_query, projection, terminal_state, and the caps (limit, max_bytes, timeout_ms) are entirely unexplained.

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 verb is specific ('Query') but the resource is described only as a 'snapshot', never stating that these are CAD source entities or what distinguishes this from siblings like inspect_source or get_entity_context_batch. The mention of 'bounded SQL filters' and 'keyset cursors' hints at a paginated entity listing, but an agent cannot confidently tell the scope apart from neighboring query 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?

There is no statement of when to use this tool, when not to, or which sibling handles a related need (e.g., get_entity_context_batch for grouped context). The only implicit usage signal is 'stable keyset cursors', which suggests resuming paginated iteration, but nothing explicit.

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