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

Annotations declare a non-destructive, non-idempotent write, and the description adds real context beyond that: the material is saved privately, and downstream asks (ask_workspace and agents) answer from it with sources. It does not address duplicate saves or what the stored item looks like, but the privacy and downstream-consumption behavior is valuable disclosure the annotations do not carry.

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, front-loaded with the trigger phrase, then the behavioral payoff, then the content limits and exclusions. Every sentence earns its place and the routing instructions are last, where they are easy to find.

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?

An output schema covers return values, so the description needn't explain them. For a 3-optional-parameter write tool it supplies the trigger, the content boundaries, the privacy/downstream behavior, and the sibling routing — everything needed 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 coverage is 100%, so the schema already documents url, text and title. The description restates the mutual exclusivity ('Give text OR url, not both') rather than adding new format constraints or syntax detail. Baseline 3 applies when the schema does the heavy lifting.

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?

"Use this when the user wants Xenition to remember material so it can answer from it later" states a specific action and the exact resource (pasted notes, policies, articles, web links). It distinguishes itself from add_note, create_document and ask_workspace by naming the ones it must not be confused with.

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?

Explicit positive case ('user wants Xenition to remember material'), explicit content constraints ('Text or a web page only; PDFs and Word files are uploaded in Xenition'), and explicit exclusions that route to named alternatives ('Do not use to create a document (use the document tools) or to answer a question now (use ask_workspace)'). Nothing is left to inference.

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