fm_save_context

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

With no annotations, the description bears full responsibility. It discloses that learning is 'saved to FM and loaded automatically at next startup' and that future sessions benefit immediately. Return type is stated as 'Confirmation message or error description.' It could mention persistence details (e.g., append vs. overwrite), but it covers key side effects.

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 well-structured: a concise opening sentence, bullet points for use cases, a persistence note, then an Args section. It is front-loaded and every sentence adds value, though it is slightly longer than necessary.

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?

Given the number of parameters and presence of output schema, the description covers purpose, usage, all parameters, and return type. It could be more specific about error handling or overwrite behavior, but overall it provides sufficient context for an AI agent to select and invoke the tool correctly.

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 coverage is 0%, so the description fully compensates. Each parameter is explained in detail (table_name, context, field_name, context_type, source) with examples, valid values for context_type, and special formatting requirements for 'value_map'. This adds meaning far beyond the bare schema.

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 clearly states the tool's purpose: 'Save an operational learning about a FileMaker field or table.' This distinguishes it from sibling tools like fm_query_records or fm_analyze, which are for reading or analyzing data, not saving learned context.

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 explicitly calls out when to use: 'Call this when you discover useful information during queries:' and lists specific scenarios (value mappings, syntax rules, etc.). It does not mention explicit alternatives or when not to use, but the use cases are clear and distinct from siblings.

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