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

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral context: it is rule-based, not a full morphological analyzer, does not reverse sandhi, and returns possible stems that need verification via get_word_definition. This goes beyond the structured annotations and gives the agent accurate expectations about the tool's limitations and output.

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 well-structured with a one-sentence summary, emoji-supported sections, and explicit bullet points for usage and limitations. It is longer than necessary but each section earns its place. The minor internal contradiction adds noise and slightly detracts from conciseness, so it does not reach a perfect 5.

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 the presence of an output schema, the description does not need to explain return values. It covers when to use, recommended workflow, limitations, and verification steps, making it quite complete. However, the compound-splitting contradiction leaves a gap in understanding, preventing a perfect score.

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?

The input schema has one parameter 'word' with a clear description ('An inflected Pāli word') and examples, achieving 100% schema coverage. The main description reinforces this with additional examples and context about what constitutes an inflected word, but it does not add meaning beyond what the schema already provides. Baseline 3 is appropriate.

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 clearly states the core function: 'Strip Pāli inflectional suffixes to find the root form (basic stem).' This specifies the verb (strip), resource (Pāli word), and the result (root form). It also distinguishes itself from sibling tools like get_word_definition by focusing on morphological analysis rather than dictionary lookup.

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 explicitly provides 'Use this tool when' bullets, a recommended workflow, and limitations. It names get_word_definition as the alternative for looking up stems. However, there is an internal contradiction: the second bullet claims you can 'split a compound,' while the Limitations section states 'Compound words (samāsa) are NOT split.' This inconsistency undermines the clarity of usage guidance, though the overall context is still helpful.

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