font_plan

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

With no annotations, the description carries the full transparency burden and does so thoroughly. It discloses that the tool is a 'pure lookup' with 'no resource cost,' never touches the network or toolchain, and does not silently recommend fonts when glyphs are missing—instead flagging 'fits: false' and 'missing_glyphs'. It also explains the optional sorting/filtering effects of size_hint and style.

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?

The description is longer than average, but every sentence adds value—detailing input modes, output contents, parameter effects, and availability. It is well-structured with clear paragraphs and example code-like strings, and despite length, there is no filler or redundancy.

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?

Given no annotations, no output schema, and 0% schema description coverage, the description is remarkably complete. It covers purpose, both invocation paths, response elements (ordered FONT_KEY_* list, minimal_character_regex), parameter semantics, and operational constraints. An agent can confidently select and invoke this tool based solely on the description.

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%, but the description fully compensates. It explains role_or_text with concrete examples and directs the check behavior, defines size_hint as 'sorts candidates by closeness to that size,' and defines style as 'filters/prefers a weight substring, e.g. bold.' All three parameters receive meaningful semantics beyond their bare titles.

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: 'Recommend Pebble system fonts for a UI role or a literal string.' It clearly distinguishes two usage modes (role vs. literal text) and even lists example roles, leaving no ambiguity about the tool's function. No sibling tool handles fonts, so differentiation is inherent.

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 explicit guidance on when to pass a role ('Pass a role like...') versus literal text ('Pass literal text instead...'), including expected outcomes for each. It also notes the tool is 'always available regardless of capability tier,' which is a useful when-to-use signal. It does not explicitly name alternatives, but none relevant exist among siblings.

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