manage_source

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

With no annotations provided, the description bears the full burden of disclosing behavior. It clearly states the operations are read/write, including the destructive delete, and outlines the request/response shape: 'Returns: dict: {"status", "url", "data"}.' It specifies the payload fields and the default instance. It doesn't mention authorization requirements or irreversible side effects explicitly, but the description of delete as 'removes it' implies the effect. This is solid behavioral transparency for a CRUD tool without annotations.

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 a bit long but well-structured with clear sections: a one-line summary, a paragraph detailing each action's HTTP method and payload, a bullet list of payload fields, an Args block, and a Returns block. Information is front-loaded with the core purpose and action semantics before details. Every sentence adds value; there's no fluff. It could be slightly tighter, but it's appropriately sized for a CRUD tool with five parameters.

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 tool's complexity (CRUD with multiple parameters and nested objects) and the absence of annotations or an output schema, the description is remarkably complete. It covers all actions, parameter requirements, payload structure, the return format, and even the default instance behavior. It also directs the agent to manage_citation for citation handling, preventing misuse. An agent can confidently invoke this tool correctly based on the description alone.

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%, so the description must fully explain each parameter. It does: action lists the allowed values, handle is marked as required for get-one/update/delete, data is required for create/update, query is described as 'optional dict of extra query-string parameters for reads,' and instance is noted as defaulting to the first from get_instances. This exceeds what the schema provides, giving an agent complete parameter semantics without needing to guess.

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 opens with a precise statement of the tool's function: 'Create, read, update or delete Gramps Source records.' It names the resource (Source records) and the four verbs, clearly distinguishing it from siblings like manage_citation, which handle a different entity. The actions are spelled out (get, create, update, delete) with concrete HTTP semantics (POST, PUT, DELETE), so an agent can immediately identify the tool's scope.

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 explains when each action is appropriate: 'action=get lists sources (handle empty) or returns one source by handle; action=create posts a full Source JSON object...' It also provides a pointer to an alternative for related data: 'Citations of a source are managed with manage_citation.' While it doesn't explicitly list exclusions or when not to use the tool, the action breakdown and the citation pointer give enough context to route correctly. It also notes the instance default, aiding selection in multi-instance setups.

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