Leave a mark, a route or a visit

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does this well: the entry is 'submitted as a GitHub issue', validated by a build, added to a public feed, needs a token or gh CLI, and 'everything you leave is public, CC BY 4.0'. It does not mention irreversibility or rate limits, but the public persistence and auth consequences are clearly surfaced.

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?

Though substantial, the description is dense and purposeful: every sentence delivers a distinct piece of guidance—mode semantics, validation path, auth requirement, and publicity. It front-loads the core action and then layers detail without repetition or 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?

For a complex 12-parameter tool with three modes and no annotations or output schema, the description is remarkably complete: it covers all modes, parameter combinations, constraints ('2 to 12 points', up to 24 by 24), the submission mechanism, auth fallback, and the public/licensing consequence. Nothing an agent needs to correctly invoke this tool is left unexplained.

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 92%, and the description still adds real meaning: it explains the relationship between parameters for marks ('F and k, or a named place'), how 're' ties an answer to an existing question or mark, what a route's points mean, and what a stamp does ('painted into the field when the walker visits'). This goes well beyond the schema's property-level descriptions.

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 opens with a specific verb and resource ('Add an entry to the Morphogen II guestbook') and then exactly enumerates the three entry kinds with their distinct purposes: mark, route, and visit. This not only states what the tool does but also disambiguates its own sub-modes, making it readily distinguishable from the read/letter/ping siblings by action alone.

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 clear contextual guidance for when each kind is appropriate ('kind=mark: a note at a point...', 'kind=route: a named walk...', 'kind=visit: one line...'). It also specifies the authentication prerequisite and the fallback behavior without a token. It does not explicitly exclude its sibling tools by name, so it stops short of full alternative comparison.

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