ShareNotes

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

Goes well beyond the annotations: discloses that anyone with the link can read the note, that storage is server-side and not end-to-end encrypted, that the default lifetime is 7 days, and what burnAfterRead actually does operationally. It also states what is returned (link and expiry time) — exactly the context the readOnlyHint=false / openWorldHint=true / idempotentHint=false annotations leave unresolved.

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?

Front-loaded with the action and the returned artifact, then purpose, then safety caveats, then optional modifiers. Every sentence carries a distinct piece of information — use case, risk, expiry default, burn behavior, return value — with no filler.

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?

No output schema exists, yet the description still names the return values (link and expiry time). For a four-parameter write tool with a public-exposure risk, it covers use case, security boundary, defaults, and returns — everything needed to call it safely and 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 100%, so the baseline is 3; the description restates the expiresIn default of 7d and the burnAfterRead destruction semantics that the schema already documents. It adds a light gloss on why one would set expiry or burn, but says nothing extra about title or content beyond 'publish 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?

States a specific verb and resource ('Publish text as a note on sharenotes.dev') and pins down the concrete artifact the agent gets back ('a short, human-readable link'). The scope is immediately distinguishable from its sibling read_note, so an agent can route correctly without inspecting either schema.

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 explicit positive triggers ('share text, code, logs or instructions with someone else, or move text to another device') and an explicit exclusion ('never use it for passwords, API keys or other secrets'). It stops short of naming an alternative channel for sensitive data or referencing the read_note counterpart, so the routing picture is clear but not fully closed.

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

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

Going beyond readOnlyHint/openWorldHint, the description discloses that editor-authored notes return HTML, that PIN-protected notes are inaccessible, and that delete-after-reading notes are refused because opening destroys them. That destruction caveat is exactly the kind of behavioral context annotations cannot express.

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 action and accepted input forms, then usage, then the refusal cases. Every sentence carries distinct information with no padding.

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 single-parameter read tool with no output schema, the description covers input formats, response format (HTML for editor notes), and the failure modes an agent must route around. Nothing needed to call it correctly is missing.

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% and the schema already gives the exact same example (full link or bare slug), so the description's restatement of accepted formats adds little. Baseline 3 applies when the schema fully documents the single parameter.

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 (read) and resource (text of a note) plus the service domain, and the read framing distinguishes it cleanly from the sibling create_note. An agent can identify the operation without opening the schema.

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?

Explicitly names the triggering condition ('when the user gives you a ShareNotes link and asks about its contents') and two exclusions (PIN-protected, delete-after-reading) with an alternative action (ask the user to open it in a browser). Both when-to-use and when-not are covered.

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