project_data_set

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

Annotations already declare the write/destructive profile; the description adds genuinely useful behavior beyond that — the data lives inside the DWG as an XRecord and survives save/reopen. It omits the consequence of setting a key that already exists (overwrite), which is the main thing the destructiveHint implies.

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?

Three tight sections — the core behavior, the when-to-use trigger, and a worked example — with zero filler and the essential mechanics front-loaded. The example line is short and directly callable.

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 need no explanation, and annotations cover the safety profile. Purpose, trigger, parameter limits and a usage example are all present, leaving only the minor overwrite-semantics gap.

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 0% schema description coverage, the description must carry parameter meaning, and it largely does: key length limit of 64 chars with no leading/trailing spaces, and value limited to 2000 characters of text. It stops short of stating key character restrictions or normalization rules, so the compensation is good but not complete.

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+resource ('Guarda um texto de projeto DENTRO do DWG') and even names the storage mechanism (XRecord dictionary 'AUTOCAD_MCP') plus its persistence across save/open. It does not, however, differentiate itself from the obvious sibling project_data_get, which is never mentioned.

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?

'QUANDO USAR' gives a concrete trigger with examples of the metadata to store (revisão, nº do documento, norma, responsável), so the agent knows when this tool applies. There is no explicit when-not and no pointer to project_data_get as the read counterpart, leaving the read/write pairing to inference.

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