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

Annotations only establish readOnlyHint=false; the description goes well beyond them by disclosing that the result is a draft, that nothing is emailed to the client, and that plan caps can trigger HTTP 426. It also names the two concrete endpoints used, which is behavior an agent cannot infer from the schema.

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?

Four dense sentences, front-loaded with the 'WRITE:' marker and the draft/non-sending fact, then template semantics, then the cap error. No sentence is redundant or restates the title.

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 9-parameter mutation with full schema coverage and no output schema, the description covers side effects, template behavior, and a failure mode. The only gap is that it never indicates what comes back (e.g., a proposal id) for chaining into bidsketch_add_proposal_section.

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 100% schema description coverage, the schema already documents all nine parameters including tax/discount fractions and date format. The description only reinforces template_id's copy-sections-and-fees behavior and its provenance from bidsketch_list_templates, which is a minor addition over the schema text.

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?

Opens with an explicit write verb plus resource ('create a proposal for a client') and adds the optional template variant. This is clearly distinguishable from bidsketch_update_proposal and bidsketch_get_proposal among the siblings.

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?

States the condition that selects the template path ('optionally from a template (template_id from bidsketch_list_templates)') and clarifies the output state ('created as a draft; this tool does not send anything to the client'). It does not explicitly route the agent to bidsketch_update_proposal for modifying an existing proposal, so the exclusion is only implied.

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