convert_caseConvert text to a target case: camel, pascal, snake, kebab, constant, title, sentence, lower, upper, dot, or slug (keyless, offline).
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The text to convert. | |
| target | Yes | Target case: camel | pascal | snake | kebab | constant | title | sentence | lower | upper | dot | slug. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesPrevious value: -[
- {
- "target": "camelCase",
- "text": "hello world example"
- },
- {
- "target": "kebab",
- "text": "convert_this_text"
- }
-]New value: +[
+ {
+ "target": "camel",
+ "text": "hello world example"
+ },
+ {
+ "target": "kebab",
+ "text": "convert_this_text"
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "target": "camelCase",
+ "text": "hello world example"
+ },
+ {
+ "target": "kebab",
+ "text": "convert_this_text"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, and non-destructive traits, but the description adds the behavioral trait 'offline' and implies 'keyless' (no authentication needed), which goes beyond annotation hints.
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?
A single sentence that is front-loaded with the core purpose and efficiently lists all target cases without extraneous words.
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 simple string transformation tool with no output schema, the description adequately explains inputs and behavior. It could mention that the output is the converted string, but this is strongly implied.
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?
With 100% schema description coverage, the description repeats the enum-like list of target cases already present in the schema's property description, adding no new meaning. Baseline 3 applies.
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 uses the specific verb 'convert' with resource 'text' and explicitly lists 11 target cases (camel, pascal, snake, etc.), clearly distinguishing this tool from siblings like 'all_cases' which may offer different functionality.
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 does not specify when to use this tool versus alternatives like 'all_cases' or other text utilities. It neither provides when-not-to-use guidance nor mentions prerequisites, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to data sources; polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, and bet_research all target prediction-market analysis; and all_cases plus convert_case both handle text-case conversion. An agent will struggle to pick the right tool without deep reading.
Nearly all names are lowercase with underscores, but the morphological pattern is mixed: some are verb_noun (convert_case, compare_entities, resolve_entity, scan_dependency), many are bare nouns (entity_profile, pipeworx_trending, polymarket_edges, all_cases), and a few are single-word verbs (forget, recall, remember). Still readable, but not a predictable verb_noun convention throughout.
33 tools is far too many for a server named 'Textcase' — only all_cases and convert_case relate to the apparent purpose. The remaining 31 constitute a sprawling assortment of data research, prediction markets, memory, subscriptions, and feedback tools that have nothing to do with text casing, making the count feel bloated and misaligned.
For the stated text-case domain, the two converters cover the basic transformations but lack supporting operations like case detection, batch processing, or custom case definitions. More fundamentally, the tool surface is incoherent: the majority of tools serve foreign domains (Pipeworx data, Polymarket, subscriptions), so there is no clear domain to evaluate for completeness, and obvious gaps exist within whatever the server is meant to be.