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

The description adds substantial behavior beyond the annotations: batch editing up to 100 files with all-or-none semantics, tag replacement, [] clearing tags, null clearing individual fields, prerequisite definitions, and per-file cost. These details are not covered by the annotations, which only state it is non-destructive, idempotent, non-read-only and not open-world.

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 front-loaded with the core action and batch limit, then lists field semantics and prerequisites. It is dense but appropriate for a 10-parameter mutation tool; the only clear waste is the duplicated cost statement ('$0.005 per file changed' appears twice).

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 complex metadata mutation with nested fields and no output schema, the description covers prerequisites, clearing behavior, batching, atomicity and cost. It could be slightly more complete by explicitly stating that omitted parameters leave existing values unchanged and by saying what a successful response contains.

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 schema description coverage is only 10%, the description compensates by explaining nearly every parameter semantically: title, notes, document_date, correspondent, document_type, tags replacement/clearing, add_tags, remove_tags, and fields with null-clearing behavior. This goes well beyond the schema types and constraints.

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 a specific verb and resource: 'Set what one file is' and lists the metadata being set. It clearly distinguishes the tool from files_define by requiring definitions first, so an agent can tell it is for editing existing file metadata rather than defining types/tags/fields.

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?

It gives a clear prerequisite: types, tags and fields must be defined first via files_define. It also contextualizes that Conecto does not file anything on its own, so the agent must decide file metadata. It does not explicitly name when to use this versus files_get or files_delete, but the editing context is clear.

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