growsurf_update_program_resource

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

Annotations declare readOnlyHint=false, destructiveHint=true, idempotentHint=true. The description adds meaningful behavioral context: only sent fields change (partial update semantics), FILE replacement requires a two-step flow with a one-time upload ticket, and campaignId targeting falls back to GROWSURF_CAMPAIGN_ID. It doesn't explicitly warn about destructive consequences, but the annotations already carry destructiveHint=true. The description adds value beyond annotations without contradicting them.

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 sentences, each dense with useful information: the core action, the FILE replacement prerequisite, and the campaignId targeting rule. No filler, no repetition of schema details. Front-loaded with the primary purpose.

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?

The tool has 12 parameters, nested objects, an output schema, and complex conditional constraints. The description covers the critical workflow (FILE replacement), the partial-update semantics, and the campaign targeting fallback. It doesn't enumerate all field constraints, but the schema already does that. The main gap is that it doesn't mention the output schema or what the response contains, but the output schema exists and the description needn't explain return values. Overall, complete enough for an agent to call it 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 description coverage is 42%, so the description must compensate for undocumented parameters. It explains the FILE replacement flow (uploadTicket/uploadResult), the position field, and the campaignId fallback. It also clarifies that url is for LINK and text is for TEXT, which the schema already states. It doesn't explain title, description, category, isPublished, or resourceId semantics, but those are fairly self-evident from their names. The description adds meaningful semantics for the trickiest parameters.

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 updates participant resource fields or moves a resource to a zero-based position, and it explicitly names the prerequisite for replacing a FILE (calling growsurf_prepare_program_resource_file). It distinguishes itself from create/delete/list resource siblings by focusing on update semantics. However, it doesn't explicitly contrast with growsurf_create_program_resource or growsurf_delete_program_resource, so it's clear but not fully differentiated.

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 gives explicit when-to-use guidance: 'Update at least one participant resource field, or move it to a zero-based position.' It also provides a critical alternative workflow: to replace a FILE, call growsurf_prepare_program_resource_file first and pass its uploadTicket and uploadResult unchanged. It also explains the campaignId targeting fallback to GROWSURF_CAMPAIGN_ID. This is strong usage guidance.

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