declare_my_tool

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

With no annotations, the description carries the full burden and does well: it discloses that the tool is unseen in ranking unless a trigger fires, is "never scored," and that stance governs whether a catalog tool can displace it. Undisclosed: duplicate-name behavior and what project_id scoping does.

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?

Dense but front-loaded — routing behavior first, then parameter rules, then the stance default. Every clause carries information; only the nested quotation styling makes it slightly harder to parse on a first read.

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 6-parameter, no-annotation, no-output-schema tool, the description covers what an agent needs to call it correctly: required triggers, their content rules, stance semantics, and routing consequences. The one real hole is project_id pairing with the session/onboard siblings.

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 must compensate, and it largely does: triggers get explicit content rules (verbatim, every condition kept, user's language), stance gets both enum values explained, and description/capabilities are labeled "report wording only." project_id is entirely undocumented in both schema and description.

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 and resource ("Declare a tool the user already has") and grounds it with a concrete user-utterance example. The routing explanation ("routes to it when a trigger fires; otherwise it is not in the ranking") makes the effect distinguishable, though no sibling such as prefer_tool or update_my_tool is named for contrast.

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?

Gives a recognizable situation for use ("use my Xero thing for invoices") and an explicit procedural rule: "No trigger given: ask for it." It also explains the default stance and when benchmarked applies. It stops short of saying when to choose update_my_tool or prefer_tool instead.

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